“And there is a whole layer of infrastructure being developed right now.” Temporal's pitch is something it calls “durable execution,” a new category Abbas says is about giving developers a simpler programming model for long-running, distributed workflows. Instead of wiring together queues, databases, retry mechanisms, and timers to handle failures, engineers write their logic as normal code and Temporal makes it durable behind the scenes. Abbas and Fateev launched Temporal in 2019, after they helped build an open-source orchestration engine called Cadence during their time at Uber. The tool was used by companies including HashiCorp, LinkedIn, Airbnb, Coinbase, and others. “Both of us have been obsessed about this problem space,” Abbas said, describing Temporal as “literally the fourth or fifth time we are building a similar system.” During the cloud era, Abbas said, Temporal became a “reliability backbone” for developers building mission-critical applications. Now, as AI models get smarter and agents hit production, the company is seeing huge scale. Temporal's customer base ranges from OpenAI, which uses the platform for image generation, to Replit, which uses Temporal to orchestrate coding agents over extended sessions. “As long-running agents become a primary driver of enterprise value, the execution layer beneath them becomes indispensable,” investors with Andreessen Horowitz wrote in a blog post. Asked about a potential AI bubble and broader hype, Abbas pointed to customers like Abridge in healthcare, where doctors can focus on patients instead of note-taking. He also noted transformation across legal workflows, coding agents, customer support, and research. Temporal is built as a remote-first company, with around 375 employees and 62 of them in the Seattle area. Abbas, who was previously CTO (he swapped roles with Fateev in 2024) said the software infrastructure expertise in Seattle is a good match for trends that Temporal is riding. As for advice to other founders riding the AI wave, Abbas said it's about getting clarity on how you deliver value and avoiding all other distractions. University of Washington scientists and students are using AI to create real medicines. Better treatments for cancer, autoimmune diseases, viruses and more are now on the horizon thanks to groundbreaking work with artificial intelligence from a team of scientists at the University of Washington's Institute for Protein Design. Led by Nobel Prize winner David Baker, this team of Huskies uses AI tools to create proteins — biology's building blocks — that lay the foundation for new medicines. ‘We're experimenting aggressively': How Expedia sees AI reshaping travel — and its own business This Seattle startup wants to turn AI prompts into shareable software Startup founder's new chapter: A vibe-coded project using human curation and AI to recommend books Temporal raises $300M, hits $5B valuation as Seattle-area infrastructure startup rides AI wave Tech Moves: Gennev founder steps down; Aurion Biotech CEO is out; Temporal adds president

It seemed obvious to me that you could make a more realistic argument and just stick to an argument which states that due to drunk driving and domestic abuse, marijuana is less harmful overall than alcohol, but is treated as more dangerous. (and yes, the other side was a bit crazy too. "When you buy weed you're supporting the same terrorism that happened on 9/11")Later research (such as this) has suggested a link between marijuana and psychosis, however the actual risk factors do seem difficult to nail down. (however, this is still a far cry from the claim that it's totally harmless)What I ultimately learned is that in a pitched political battle, people actually damage their credibility because they're afraid to cede _any_ ground to the opposition, even when that means making unrealistic claims. A centrist (or just someone who is undecided) is not really taken in as much by these extremist argument, and to their eyes it damages the credibility of one or both sides. Later research (such as this) has suggested a link between marijuana and psychosis, however the actual risk factors do seem difficult to nail down. (however, this is still a far cry from the claim that it's totally harmless)What I ultimately learned is that in a pitched political battle, people actually damage their credibility because they're afraid to cede _any_ ground to the opposition, even when that means making unrealistic claims. A centrist (or just someone who is undecided) is not really taken in as much by these extremist argument, and to their eyes it damages the credibility of one or both sides. What I ultimately learned is that in a pitched political battle, people actually damage their credibility because they're afraid to cede _any_ ground to the opposition, even when that means making unrealistic claims. A centrist (or just someone who is undecided) is not really taken in as much by these extremist argument, and to their eyes it damages the credibility of one or both sides. Because there are plenty of proponents who are not that... in fact 64% of Americans support making weed legal (2025), so it'd be really unfair to judge that movement based on those old experiences. The anti-legalization side had a few odd arguments as well, and some old claims that were unfounded. I think both mdma and marijuana cause anxiety and they mess with short term memory.There doesn't seem to be a good answer to protecting kids from drugs. Heavily regulated legalisation might help or it might normalise drug use.As an aside I personally think alcohol in very moderate use isn't really as harmful as other drugs. Heavily regulated legalisation might help or it might normalise drug use.As an aside I personally think alcohol in very moderate use isn't really as harmful as other drugs. this is also just motivated reasoningThe insanity of the fringe pro-legalization arguments has no bearing on whether legalization is a good idea or not.> When I would see friends/family that started smoking regularly become noticeably less intelligent while pro-legalization proponents would argue there are no negative side-effectsThis is also just ripe for cognitive bias which is why we should use science to understand these types of claims. The insanity of the fringe pro-legalization arguments has no bearing on whether legalization is a good idea or not.> When I would see friends/family that started smoking regularly become noticeably less intelligent while pro-legalization proponents would argue there are no negative side-effectsThis is also just ripe for cognitive bias which is why we should use science to understand these types of claims. > When I would see friends/family that started smoking regularly become noticeably less intelligent while pro-legalization proponents would argue there are no negative side-effectsThis is also just ripe for cognitive bias which is why we should use science to understand these types of claims. This is also just ripe for cognitive bias which is why we should use science to understand these types of claims. The thing is, I 100% agree with your reasons for why it should be outlawed. I just think those are reasons to discourage using it, especially chronically.However, I wholeheartedly believe the government should not have any say in how anyone lives their life, and treats their own body. However, I wholeheartedly believe the government should not have any say in how anyone lives their life, and treats their own body. Imagine if the oil industry starts paying people to go throw soup on paintings just to make the pro “let's prevent climate change” people look stupid.Oh. Largely any movement has people with insane takes, and it's impossible to tell the difference between good and bad faith actors.That, and sometimes people just aren't trying to be persuasive at all. It's extremely rare to actually see someone persuaded about anything political without enormous amount of effort, or more realistically a change in material interests. That, and sometimes people just aren't trying to be persuasive at all. It's extremely rare to actually see someone persuaded about anything political without enormous amount of effort, or more realistically a change in material interests. There have been some claims that it helps alleviate nausea associated with chemotherapy, which is quite reasonable and will likely be proved out by evidence over time.Really … who genuinely claimed it “cures” cancer? Legal for anyone at any age?Edit: To put it another way, what's the ground that has been ceded here? Legal for anyone at any age?Edit: To put it another way, what's the ground that has been ceded here? Edit: To put it another way, what's the ground that has been ceded here? I'm very involved in legalization and I don't know anyone that is for legalization that thinks any of those things, never even heard anyone say such garbage. I think you may be cherry-picking the crazy here. This was over 20 years ago, long before "nut-picking" became impossible to avoid. They may have had had extreme views, but this was long before modern social media surfaced only the craziest people for any given position.>Using the most anecdotally crazy people you met to suggest that the pro-legalization movement is crazy, is frankly, crazy.Also, I disagree with this characterization. I am not crazy, it was unnecessarily rude to suggest otherwise. >Using the most anecdotally crazy people you met to suggest that the pro-legalization movement is crazy, is frankly, crazy.Also, I disagree with this characterization. I am not crazy, it was unnecessarily rude to suggest otherwise. I am not crazy, it was unnecessarily rude to suggest otherwise. You suggested the legalization movement is "crazy", without context. That's the only way we can take your original comment, so if you don't like being called out like this, then be a lot more specific and say it was only your crazy friend group that was crazy, making it very anecdotal and not overly broad. That's the only way we can take your original comment, so if you don't like being called out like this, then be a lot more specific and say it was only your crazy friend group that was crazy, making it very anecdotal and not overly broad. That's the only way we can take your original comment, so if you don't like being called out like this, then be a lot more specific and say it was only your crazy friend group that was crazy, making it very anecdotal and not overly broad. That's the only way we can take your original comment, so if you don't like being called out like this, then be a lot more specific and say it was only your crazy friend group that was crazy, making it very anecdotal and not overly broad. What happened is that the people making these disengenuous comments in bad faith did not realize that so many others would watch them and without understanding hte context woudl pick up those same disingenuous arguments and take them as truth.This is all the long term consequences of allowing Reefer Madness tier propaganda be published and not repudiated immediately. This is all the long term consequences of allowing Reefer Madness tier propaganda be published and not repudiated immediately. Hm, but this does not exclude the possibility that the being prone to mental illness comes with a little bit higher tendency to consume cannabis... Methamphetamine and PCP might take issue with this statement. I think only young people in their weed honeymoon phase get defensive about this. I am not saying anyone should or should not use these substances, but that was enough of a lesson for me to know never to touch that stuff. But also let's remember that there are tens of million Americans using weed products (legally in many states) who are having a great time with it. If anyone is curious, check out brands like Rove, Dompen, Care By Design, which offer THC pens at very low dosage. If you compare the literal amount of THC consumed, it's an almost 20x reduction. If you compare the literal amount of THC consumed, it's an almost 20x reduction. Has anyone done diff-in-diffs of US states and simply looked at eg mental health diagnoses or hospital admissions? "Based on data from 2023–2025, approximately 15% to 17% of American adults currently consume cannabis." - GallupSo though this may be technically true in some sense, it should also be understood that if cannabis had any major immediate drastic effects we would have noticed them decades ago. Perhaps weed, like alcohol, needs a legal minimum age of 21. So though this may be technically true in some sense, it should also be understood that if cannabis had any major immediate drastic effects we would have noticed them decades ago. Perhaps weed, like alcohol, needs a legal minimum age of 21. Generally, it already does have a legal minimum age of 21. Very few things in life pass that test, which is why we have research studies When it's a drug more than 10% of the US population uses, we can immediately say the risk increase can't really be that big or we'd have noticed it by now.Edit: after looking at the paper, it looks like among the weed group the prevalence is roughly twice as high -- so instead of 1/100 having psychotic issue it'd be 2/100... and again for people who used when they were 13-17 year olds, which is underage in every state.So you could frame that as doubling the risk OMG, or a 1 percentage point increase in risk, or it could all just be self-medicating, we really don't know much. Edit: after looking at the paper, it looks like among the weed group the prevalence is roughly twice as high -- so instead of 1/100 having psychotic issue it'd be 2/100... and again for people who used when they were 13-17 year olds, which is underage in every state.So you could frame that as doubling the risk OMG, or a 1 percentage point increase in risk, or it could all just be self-medicating, we really don't know much. So you could frame that as doubling the risk OMG, or a 1 percentage point increase in risk, or it could all just be self-medicating, we really don't know much. If it was something like 10% - 20%, it might be noise or some other factor, but that big a number is real. The actual paper doesn't, and merely implies correlation. Western medicine can't even explain any of these ailments, where it comes from, how it happens, what triggers it but so many cannabis users shield and attack any new research or study that questions the risks of cannabis for the young.If it truly is harmless then are those same people suggesting that they light up a joint with their children ? Doctors hand out edibles when they catch a cold or can't sleep?While I do think there are deeply helpful properties of cannabis we are still early, new research is only beginning to come out as it gets scrutiny. It took us many decades to learn the harmful effects of tobacco while for a long time everybody just shrugged it off as conspiracy. Many see money to be made or their political statement that they will defend vigorously. The real risks that I see is raising the THC % content to extreme levels for chronic users who built a large tolerance through long term habitual use and claim they aren't addicted, proliferation of white/grey dispensaries that make it even more accessible to the young. This really needs to be addressed when we don't even understand the mechanisms or can reliably explain the after effects of those risks coming to fruition. If it truly is harmless then are those same people suggesting that they light up a joint with their children ? Doctors hand out edibles when they catch a cold or can't sleep?While I do think there are deeply helpful properties of cannabis we are still early, new research is only beginning to come out as it gets scrutiny. It took us many decades to learn the harmful effects of tobacco while for a long time everybody just shrugged it off as conspiracy. Many see money to be made or their political statement that they will defend vigorously. The real risks that I see is raising the THC % content to extreme levels for chronic users who built a large tolerance through long term habitual use and claim they aren't addicted, proliferation of white/grey dispensaries that make it even more accessible to the young. This really needs to be addressed when we don't even understand the mechanisms or can reliably explain the after effects of those risks coming to fruition. While I do think there are deeply helpful properties of cannabis we are still early, new research is only beginning to come out as it gets scrutiny. It took us many decades to learn the harmful effects of tobacco while for a long time everybody just shrugged it off as conspiracy. Many see money to be made or their political statement that they will defend vigorously. The real risks that I see is raising the THC % content to extreme levels for chronic users who built a large tolerance through long term habitual use and claim they aren't addicted, proliferation of white/grey dispensaries that make it even more accessible to the young. This really needs to be addressed when we don't even understand the mechanisms or can reliably explain the after effects of those risks coming to fruition. Many see money to be made or their political statement that they will defend vigorously. The real risks that I see is raising the THC % content to extreme levels for chronic users who built a large tolerance through long term habitual use and claim they aren't addicted, proliferation of white/grey dispensaries that make it even more accessible to the young. This really needs to be addressed when we don't even understand the mechanisms or can reliably explain the after effects of those risks coming to fruition. Drug use among vulnerable populations increases the risk of psychotic episodes, but does not increase the risk of developing those conditions. There is no difference in the rate of extreme psychological outcomes among drug users and non-drug users, and in fact, this study reinforces that observation - only 4,000 of 460,000 had those negative outcomes. Over the next 20 years, it's extrmeely likely that another 600-1000 will develop schizophrenia, even abstaining from drugs entirely. Drug use can trigger a psychotic episode and result in long term schizophrenia; by the time you turn 45, however, your odds of a schizophrenic break drop to almost 0.The worst part of drug use and mental health outcomes is that it can rob people of normal years of life, and rarely, result in schizophrenic or other psychotic conditions being triggered when they might never have been. However, this is not just marijuana or other illegal drugs, but alcohol, caffeine, trauma or intense stress, and even chronic health issues can have the same outcome.This study also fails to account for the confounding fact that people with mental health issues often pursue mind altering drugs in order to self medicate. Consult a doctor, and if you have risk factors, live your life accordingly.If you don't have risk factors for schizophrenia, drug use will not suddenly put you at risk of developing it. Marijuana or other recreational drug use will not cause you to have a psychotic episode. If you do have risk factors, then you're twice as likely to have an episode by using drugs or experiencing other triggers than otherwise.For those who are susceptible, your relative risk of psychotic episodes and mental breakdown double under mairjuana and other substance use.For those who are not susceptible, your absolute risk of psychotic episodes and mental breakdown remain near 0. Drugs don't induce these conditions (except in the case of extreme stimulant abuse, and possibly extreme psychedelics outcomes, although getting fried by psychedelics isn't really the same thing as psychosis. The worst part of drug use and mental health outcomes is that it can rob people of normal years of life, and rarely, result in schizophrenic or other psychotic conditions being triggered when they might never have been. However, this is not just marijuana or other illegal drugs, but alcohol, caffeine, trauma or intense stress, and even chronic health issues can have the same outcome.This study also fails to account for the confounding fact that people with mental health issues often pursue mind altering drugs in order to self medicate. Consult a doctor, and if you have risk factors, live your life accordingly.If you don't have risk factors for schizophrenia, drug use will not suddenly put you at risk of developing it. Marijuana or other recreational drug use will not cause you to have a psychotic episode. If you do have risk factors, then you're twice as likely to have an episode by using drugs or experiencing other triggers than otherwise.For those who are susceptible, your relative risk of psychotic episodes and mental breakdown double under mairjuana and other substance use.For those who are not susceptible, your absolute risk of psychotic episodes and mental breakdown remain near 0. Drugs don't induce these conditions (except in the case of extreme stimulant abuse, and possibly extreme psychedelics outcomes, although getting fried by psychedelics isn't really the same thing as psychosis. This study also fails to account for the confounding fact that people with mental health issues often pursue mind altering drugs in order to self medicate. Consult a doctor, and if you have risk factors, live your life accordingly.If you don't have risk factors for schizophrenia, drug use will not suddenly put you at risk of developing it. Marijuana or other recreational drug use will not cause you to have a psychotic episode. If you do have risk factors, then you're twice as likely to have an episode by using drugs or experiencing other triggers than otherwise.For those who are susceptible, your relative risk of psychotic episodes and mental breakdown double under mairjuana and other substance use.For those who are not susceptible, your absolute risk of psychotic episodes and mental breakdown remain near 0. Drugs don't induce these conditions (except in the case of extreme stimulant abuse, and possibly extreme psychedelics outcomes, although getting fried by psychedelics isn't really the same thing as psychosis. Consult a doctor, and if you have risk factors, live your life accordingly.If you don't have risk factors for schizophrenia, drug use will not suddenly put you at risk of developing it. Marijuana or other recreational drug use will not cause you to have a psychotic episode. If you do have risk factors, then you're twice as likely to have an episode by using drugs or experiencing other triggers than otherwise.For those who are susceptible, your relative risk of psychotic episodes and mental breakdown double under mairjuana and other substance use.For those who are not susceptible, your absolute risk of psychotic episodes and mental breakdown remain near 0. Drugs don't induce these conditions (except in the case of extreme stimulant abuse, and possibly extreme psychedelics outcomes, although getting fried by psychedelics isn't really the same thing as psychosis. It comes down to susceptibility - genetics and health conditions play into this. Consult a doctor, and if you have risk factors, live your life accordingly.If you don't have risk factors for schizophrenia, drug use will not suddenly put you at risk of developing it. Marijuana or other recreational drug use will not cause you to have a psychotic episode. If you do have risk factors, then you're twice as likely to have an episode by using drugs or experiencing other triggers than otherwise.For those who are susceptible, your relative risk of psychotic episodes and mental breakdown double under mairjuana and other substance use.For those who are not susceptible, your absolute risk of psychotic episodes and mental breakdown remain near 0. Drugs don't induce these conditions (except in the case of extreme stimulant abuse, and possibly extreme psychedelics outcomes, although getting fried by psychedelics isn't really the same thing as psychosis. If you don't have risk factors for schizophrenia, drug use will not suddenly put you at risk of developing it. Marijuana or other recreational drug use will not cause you to have a psychotic episode. If you do have risk factors, then you're twice as likely to have an episode by using drugs or experiencing other triggers than otherwise.For those who are susceptible, your relative risk of psychotic episodes and mental breakdown double under mairjuana and other substance use.For those who are not susceptible, your absolute risk of psychotic episodes and mental breakdown remain near 0. Drugs don't induce these conditions (except in the case of extreme stimulant abuse, and possibly extreme psychedelics outcomes, although getting fried by psychedelics isn't really the same thing as psychosis. For those who are susceptible, your relative risk of psychotic episodes and mental breakdown double under mairjuana and other substance use.For those who are not susceptible, your absolute risk of psychotic episodes and mental breakdown remain near 0. Drugs don't induce these conditions (except in the case of extreme stimulant abuse, and possibly extreme psychedelics outcomes, although getting fried by psychedelics isn't really the same thing as psychosis. For those who are not susceptible, your absolute risk of psychotic episodes and mental breakdown remain near 0. Drugs don't induce these conditions (except in the case of extreme stimulant abuse, and possibly extreme psychedelics outcomes, although getting fried by psychedelics isn't really the same thing as psychosis. To me it doesn't seem like they control much for confounding factors, or the possibility that young people who might develop psychiatric illness could also be more drug seeking or irresponsible in their drug use. Curiously I see this as a pro-legalization arguement, if it were available in a shop I could select a mild flavour, rather than the skunk that the criminals grew, and is all that is on offer It may have gotten better but I think manufacturing consistency isn't good either. Highest I've ever been was from a single “2.5 mg” They excluded people with a mental health diagnosis, and their data for already having symptoms was having a diagnosis?Why do they assume this shows marihuana causes mental disorders, as opposed to being undiagnosed whilst already showing symptoms leads to self medication, for example?I'm sorry, but most psychology research is just so incredibly badly done. Why do they assume this shows marihuana causes mental disorders, as opposed to being undiagnosed whilst already showing symptoms leads to self medication, for example?I'm sorry, but most psychology research is just so incredibly badly done. I'm sorry, but most psychology research is just so incredibly badly done.

Time is running out to get your nominations in for the 2026 GeekWire Awards. If you want to help us recognize the outstanding tech entrepreneurs, innovators, deal makers and nonprofit leaders across the Pacific Northwest, submit a nomination today! Community nominations will close this Wednesday, Feb. 25, for the annual event, which takes place May 7 in Seattle. The GeekWire Awards, presented by Astound Business Solutions, will take place at Showbox SoDo and feature a VIP reception, sit-down dinner and fun entertainment mixed in. Past winners are not eligible in the same category. Thanks to the 2026 GeekWire Awards sponsors: Presenting sponsor Astound Business Solutions. Gold sponsors: JLL, Baird, First Tech, Amazon Sustainability, BECU, and Wilson Sonsini. PREVIOUSLY: GeekWire Awards 2025 revealed: Community ‘alive and well' at annual celebration of best in tech Click for more about underwritten and sponsored content on GeekWire. Have a scoop that you'd like GeekWire to cover? 2026 GeekWire Awards nominations open — help honor the best in Pacific Northwest tech Help us honor the best in Pacific Northwest tech Last call for GeekWire Awards nominations: Help honor tech entrepreneurs, innovators and more

Save up to $680 on your pass with Super Early Bird rates. After initially testing its AI-powered “Prompted Playlists” feature in New Zealand and recently launching in the U.S. and Canada, Spotify announced on Monday that it's rolling out the tool to Premium subscribers in the U.K., Ireland, Australia, and Sweden. Instead of searching for individual songs or artists, users can describe the vibe, scenario, or inspiration they want, and Spotify will take care of the rest. The feature is designed to interpret themes including moods, aesthetics, and even memories. For those whose musical tastes constantly evolve, playlists can be scheduled to automatically refresh on a daily or weekly basis. Since this is still in beta, Spotify noted that there might be changes as the company gets feedback, and that there are currently usage limits in place. Some users have reported hitting limits after roughly 20 or 30 prompts. Spotify has recently expanded AI features throughout its platform, including Page Match, which lets users scan a physical book page to jump to the corresponding spot in the audiobook, and About This Song. The platform also updated its song lyrics feature to provide global translations and offline access. Last week, SeatGeek partnered with Spotify to help listeners easily find ticket links for concerts on an artist's page or upcoming tour dates within the app. Internally, the company has implemented AI throughout its workflows, with co-CEO Gustav Söderström saying earlier this month that Spotify's best developers haven't written a line of code since December, thanks to AI. Spotify is also expanding its audiobook business by venturing into physical book sales. Hear from 250+ tech leaders, dive into 200+ sessions, and explore 300+ startups building what's next. Bill Gurley says that right now, the worst thing you can do for your career is play it safe Sam Altman would like to remind you that humans use a lot of energy, too Google VP warns that two types of AI startups may not survive Great news for xAI: Grok is now pretty good at answering questions about Baldur's Gate FBI says ATM ‘jackpotting' attacks are on the rise, and netting hackers millions in stolen cash Meta's own research found parental supervision doesn't really help curb teens' compulsive social media use

Mirroring similar retreats from electrification made by other high-end automakers recently, the company announced the car will no longer be put into production. Speaking to WIRED, the carmaker's chief executive, Stephan Winkelmann, says that after a year of talking to dealers and looking at market and customer data, “it was clear not only that the acceptance of full electric cars is flattening worldwide for our type of cars, it's going almost to zero—if not to zero.” Winkelmann says that although Lamborghini is ready for electric car manufacturing, “the [high-end] market is not.” As a result, Winkelmann says that the brand decided “in the last few weeks or days” that its first model in the next era for Lamborghini powertrains will be not full EV but a plug-in hybrid. “So by the end of this decade, all four [Lamborghinis] are going to be hybrids, and not, as we said, two of them electric,” Winkelmann says, confirming that this new hybrid will arrive in 2029. This move from Lamborghini underlines the parlous state of luxury EVs at present, a trend WIRED has charted. Bentley announced in late 2024 that it's pushing its electric plans back five years to 2035, blaming poor EV demand and weak charging infrastructure. Despite the imminent launch of the electric Cayenne, Porsche, faced with plummeting operating profits, has taken a huge financial hit to dramatically scale back its electrification efforts. Mercedes, instead of going fully EV by 2030, is now planning to keep gas and hybrid cars on sale for longer. CEO Ola Källenius has called this a “course correction,” admitting that EV sales have been slower than expected. Only the US bucked this trend, seeing flat growth in 2025, about 1 percent. Tesla fared worse, dropping in scale and profitability, with deliveries down 9 percent compared to 2024. “Basically all but one of the models available in Europe last year posted declines,” he says. “The discussion was based on a lot of data. “Manufacturers throughout the automotive industry are reevaluating their electric vehicle plans as they weigh demand against current economic conditions," says Philip Nothard, Cox Automotive's insight director. “For luxury brands, which operate lower volumes and higher R&D costs, these challenges are even more pronounced.” I ask if Winkelmann can explain why luxury EVs are failing so badly when lower price points in the sector are doing so well. “First of all, there is no need to buy a car like Lamborghini. Then, for sure, there is the experience with electric cars on purchase price, resale value, and residual value, and also in terms of technology.” Here Winkelmann is referring to the eye-watering drops in value some high-end EVs are experiencing, with brands like Porsche losing up to half the car's value in just a year. Meanwhile, other marques had lux EVs that lost more than $600 each day. “Then there is the fact that technology, in the eyes of our customers, is going to be obsolete in 10 years from now,” says Winkelmann, “because there's a lot of new tech. Winkelmann says he does not know if fast-charging and high-capacity solid-state battery technology will be developed in time for the brand's new deadline of 2029, however. The announcement is another reminder that Ferrari, already irrevocably committed to launching its first full EV, the Luce, later this year, is yet another luxury automaker that has chosen (or been forced) to dramatically scale back its EV plans. However, Daniele Ministeri, senior consultant at automotive analysts JATO, says that this need not spell disaster for the Italian brand's first electric car. “Ferrari has already faced criticism in the past for certain product decisions, most notably for introducing a SUV, the Purosangue,” he says. “However, two years after its launch, the Purosangue has proven to be a commercial and brand success, quickly becoming one of Ferrari's best‑selling models. Still, Ferrari has successfully drawn strong attention to the project.” Munoz says that although Europe is not the largest market for EVs, it is still the second after China, which gives an idea of how difficult it has been for these cars to gain traction. “When it is about supercars, the transition is even more difficult,” he says, “because they are usually associated to big petrol engines with a loud sound. Ferrari's upcoming EV will face tough times to compete against its own ICE siblings. In your inbox: Maxwell Zeff's dispatch from the heart of AI Big Tech says AI will save the planet—it doesn't offer much proof WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.

This describes almost perfectly what Asha Sharma will be attempting to do in her new role leading Microsoft's Xbox and video-game business: She'll need to take all the patterns she's observed as an executive with Facebook, Instacart, Seattle startup Porch, and Microsoft's AI platform, and apply them to a world she hasn't played in before. She didn't mention on the podcast speed round that it's a story about video games. But it is now, given the news Friday that Sharma will succeed 38-year Microsoft veteran Phil Spencer as CEO of Microsoft Gaming, in a shakeup that also saw Xbox President Sarah Bond — previously seen as Spencer's likely successor — decide to leave. Sharma was a surprise pick, in part because she has no prior video-game industry leadership experience, and limited background as a gamer, which is creating skepticism in gaming circles already. However, she has experience running large tech platforms, the clear trust of Microsoft CEO Satya Nadella, and a belief in the potential of AI to reshape every business. On that last point, she quickly offered some reassurance to Microsoft employees and the broader universe of Xbox gamers in her introductory memo last week. “As monetization and AI evolve and influence this future, we will not chase short-term efficiency or flood our ecosystem with soulless AI slop,” she wrote. Sharma laid out three priorities in the memo: great games above all else, a recommitment to Xbox's core console fans, and what she called the “future of play” — new business models and a shared platform where developers and players can create together. Her first act was promoting longtime studio chief Matt Booty to executive vice president and chief content officer, pairing her platform background with his decades of gaming credibility. Under Spencer, the company made massive bets on expansion, acquiring ZeniMax Media and its family of studios — including Bethesda — for $7.5 billion in 2021, and then closing the $69 billion acquisition of Activision Blizzard in 2023, the largest gaming deal in history. That brought Call of Duty, World of Warcraft, Candy Crush, Diablo, and Overwatch under Microsoft's roof, making it the third-largest gaming company in the world by revenue. Spencer also expanded Xbox's reach across PC, mobile, and cloud gaming, and built Game Pass into a major subscription service, transforming the division's business model. Xbox's challenge has not been a lack of talent or popular franchises. GeekWire gaming contributor Thomas Wilde observed that the biggest problem has been instability: waves of layoffs and studio closures that left even successful teams uncertain about their future. In his memo about the transition, Nadella said Sharma brings “deep experience building and growing platforms, aligning business models to long-term value, and operating at global scale.” Sharma's career and biographical details have been widely scrutinized over the past few days, as the video game and business press have scrambled to figure out who this person is, who arrived seemingly out of the blue to lead one of Microsoft's biggest consumer brands. As of last fall, she was a second-degree black belt in Taekwondo, explaining to Rachitsky on his podcast that the discipline is “more mental than it is physical.” What's lesser known is that she got her start at Microsoft, interning at the company and then working in marketing right out of college before leaving to help build Porch, the Seattle home services company, where she was COO during the company's early years. In a 2024 interview with GeekWire at Microsoft's Build developer conference, not long after rejoining the company, Sharma talked about what brought her back. After years working across different types of organizations, she said, the lesson she drew from her career was the importance of working with great people on problems that matter. She described feeling fortunate to be working on “some of the most important technology of our lifetime” at a critical juncture, with people embracing a growth mindset. Part of what made Spencer so beloved among Xbox fans was that he was one of them — a lifelong gamer with a prolific achievement history and a habit of wearing gaming T-shirts under blazers at industry events. Over the weekend, she began engaging directly with Xbox fans on social media, sharing her gamertag (AMRAHSAHSA, her name spelled backwards) and listing her top three games as “Halo, Valheim, Goldeneye” — Microsoft's flagship franchise, a popular survival game, and classic title that first launched on the Nintendo 64 in 1997. Longtime exec Aaron Greenberg, the division's VP of marketing, wrote on X that after spending time with Sharma during the past week, he was “incredibly optimistic about the opportunity ahead under her leadership,” describing her as “exceptionally bright, eager to listen and learn from others, no ego.” The activity history in Sharma's Xbox profile, which IGN and Windows Central quickly dissected, shows she's played about 30 titles since mid-January, gravitating toward narrative-driven indie games like Firewatch, Gone Home, and What Remains of Edith Finch — the kinds of games you'd play if you wanted to understand games as art, not just entertainment. It was a Halo: Master Chief Collection milestone, fittingly titled “Your Journey Begins.” Click for more about underwritten and sponsored content on GeekWire. Xbox chief Phil Spencer retiring after 38 years at Microsoft; Asha Sharma named new gaming CEO Tech Moves: Microsoft CVP joins Home Depot board; Impinj COO resigns; Amazon vets depart

ET on Monday, poweroutage.us showed outages affecting nearly 647,000 customers across seven northeastern states: Massachusetts, New Jersey, Delaware, Rhode Island, Maryland, New York, and Pennsylvania. EverSource, the most disrupted utility, reported roughly 207,000 outages across Connecticut, Massachusetts, and New Hampshire. In a televised interview with Hartford CBS affiliate WFSB early Monday morning, EverSource spokesperson Jamie Ratliff described the storm conditions as “very difficult” and said that high winds and snow-covered roadways are hindering restoration efforts. “This storm is far from over,” Ratliff said. This powerful Nor'easter is comparable in strength to a Category 2 hurricane, meteorologist Ben Noll reports for the Washington Post. The storm's outer bands reached the Northeast on Sunday and have since dumped more than a foot (30.5 centimeters) of snow on several cities, including New York City, Newark, New Jersey, and New Haven, Connecticut, according to Reuters. Meteorologists have also recorded wind gusts of 50 to 70 miles per hour (80 to 113 kilometers per hour) across the impacted region. The combination of heavy snowfall and high winds is continuing to produce widespread blizzard conditions, forcing officials to issue citywide (and in some cases, statewide) travel bans as blowing snow covers roadways and drastically reduces visibility. In New York City, which is battling its first blizzard in a decade, travel will remain restricted until 12 p.m. While blizzard conditions should begin to subside Monday afternoon, the storm won't depart New England until the evening, Noll reports. “Very heavy snowfall rates upwards of [2 to 3 inches (5 to 8 centimeters)] per hour and gusty winds of 40-70 mph will continue to batter the Northeast today, while also spreading into New England this morning as the storm begins to accelerate,” the National Weather Service stated in its latest update. The number of customers without power will likely climb throughout Monday as crews struggle to keep up with the damage. Impacted utilities, including EverSource, PSE&G, and Rhode Island Energy, have stated that restoration could take several days. If you also lose heat, there are steps you can take to protect yourself, your family, and your pipes from below-freezing temperatures. Immediately seal off any unused rooms, close curtains and blinds, and gather in a single, well-insulated interior room to prevent heat from escaping. Most importantly, figure out where you can go if your home becomes dangerously cold. Take the time now to locate warming shelters, community centers, or other safe indoor locations that you can reach via unrestricted means of travel. The full severity of this storm's impact remains to be seen, but it's already going to go down in history as one of the worst blizzards the Northeast has ever seen. Subscribe and interact with our community, get up to date with our customised Newsletters and much more. The first images from the European Space Agency's MTG-S satellite offer an early look at how the mission will improve weather forecasting across Europe and Northern Africa. Meteorologists are tracking another major storm system that could exacerbate lingering impacts from last weekend's Winter Storm Fern. It's looking increasingly likely that a coastal storm could bring more snow to the East Coast this weekend—and potentially strengthen into a bomb cyclone.

The defense to training with copyright is that it is the same as how humans learn from copyrighted material. The storage or reproduction is a red herring. Humans can also reproduce copyrighted works from memory as well. Showing that machines can reproduce copyrighted material is no different than saying that a human can reproduce copyright material that the human learned from.The defense to actually reproducing a work is that in order to do so, the user has to "break" the system. It is the same as how you can make legal software do illegal things (e.g. screen recorder to "steal" a movie)None of this is to say that these defenses are correct/moral; but rather that this article doesnt add any additional input into whether it is or isnt. It is the same as how you can make legal software do illegal things (e.g. screen recorder to "steal" a movie)None of this is to say that these defenses are correct/moral; but rather that this article doesnt add any additional input into whether it is or isnt. None of this is to say that these defenses are correct/moral; but rather that this article doesnt add any additional input into whether it is or isnt. Ultimately this is a matter for the courts and the law, but I'd just like to point out that a human memorizing a work, reproducing it, and distributing it is just as much a copyright violation as doing a more mechanical form of reproduction.There's a reason that fan fiction routinely falls afoul of copyright. There's quite a lot of case law in this area, and hand-waving "humans can do it too" doesn't really make for a strong argument. Humans get in trouble for it ALL THE TIME. The consequences can be fines, injuctions, or even criminal liability.I'm not sure why you think AI gets off the hook here. There's a reason that fan fiction routinely falls afoul of copyright. There's quite a lot of case law in this area, and hand-waving "humans can do it too" doesn't really make for a strong argument. Humans get in trouble for it ALL THE TIME. The consequences can be fines, injuctions, or even criminal liability.I'm not sure why you think AI gets off the hook here. I'm not sure why you think AI gets off the hook here. Who's liable for the copyright infringement if you can coax it out of a system? If you can bypass paywalls by using google's cache feature (or since they got rid of it, but using carefully crafted queries to extract the entire text via snippets), is google on the hook or the person doing it? There's plenty of people prosecuted for running illegal streaming sites and torrenting (which involves uploading), but I don't know of any efforts to crack down on non-distributors. Google might not be the most sympathetic defendant, but what about libraries? If you put the two together, you get a copyright infringement operation, all enabled by the library. Should libraries be on the hook too? Google serves (used to serve) to its users whatever the website presents to its crawler, it does not try to avoid paywalls or interact with the website in any capacity other than requesting information Humans are not judged on the basis of what they _can_ do.Reasoning about how to constrain tools on the basis of what they _could_ do, if e.g. used outside their established guardrails, needs to be very nuanced. Reasoning about how to constrain tools on the basis of what they _could_ do, if e.g. used outside their established guardrails, needs to be very nuanced. No humans can memorize entire novels, as this research proved these models do. https://en.wikipedia.org/wiki/Hafiz_(Quran)It's not far fetched to think that people could recite books just like an LLM. I don't know why they'd want to, but that's neither here nor there. It's not far fetched to think that people could recite books just like an LLM. I don't know why they'd want to, but that's neither here nor there. Humans can however, remember entire songs, and songs are definitely long enough to be considered copyright protected. There is still a difference in scale, but that's not really relevant when it comes to copyright law. You can't be like "well humans are committing copyright infringement but since it's limited to a few hundred words we'll give it a pass". For 99.999% of people that are singing a song, it's not a replacement for the original in any way shape or form, hard stop. Let's not pretend it could even get anywhere close.For the last 0.001%, we would call it a cover and typically the individually doing a cover takes some liberties of their own, still making it not a replacement in any way. For the last 0.001%, we would call it a cover and typically the individually doing a cover takes some liberties of their own, still making it not a replacement in any way. You realize that lyrics are often written by someone other than the actual singer, and whoever wrote the lyrics is entitled to compensation too? The "amateur singing isn't a replacement for the studio album" excuse doesn't work in this context. Also courts have ruled that lyrics themselves are protected by copyright.https://en.wikipedia.org/wiki/Lyrics#Copyright_and_royalties>Artists are typically cool with covers.Artists being "cool" with something doesn't mean they're not violating copyright law. https://en.wikipedia.org/wiki/Lyrics#Copyright_and_royalties>Artists are typically cool with covers.Artists being "cool" with something doesn't mean they're not violating copyright law. >Artists are typically cool with covers.Artists being "cool" with something doesn't mean they're not violating copyright law. Artists being "cool" with something doesn't mean they're not violating copyright law. You were specifically calling out individuals singing a song, not publishing lyrics online. Again your distribution/consumption model matters here.On artists being "cool" with it - if the copyright holder doesn't pursue you then does it matter? The only valid argument I would see here is if the copyright holder doesn't know about the infringement and therefore cannot seek remedies, but we can fish for illegal scenarios all day if we would like: that's not useful though. On artists being "cool" with it - if the copyright holder doesn't pursue you then does it matter? The only valid argument I would see here is if the copyright holder doesn't know about the infringement and therefore cannot seek remedies, but we can fish for illegal scenarios all day if we would like: that's not useful though. >You were specifically calling out individuals singing a song, not publishing lyrics online. Again your distribution/consumption model matters here.I'm not sure why you're so confidently dismissive here. I wasn't trying to claim that nobody owned the lyrics. I brought that point up because even in the case of an amateur singing a song, even if you accept the "for 99.999% of people that are singing a song, it's not a replacement for the original in any way shape or form" excuse, you're still infringing on the copyright of the lyrics, because it's a derivative work. Moreover it's unclear whether that excuse even works. If you make a low cost version of star wars, copying the screenplay exactly, that still seems like copyright infringement, even if "it's not a replacement for the original in any way shape or form".>On artists being "cool" with it - if the copyright holder doesn't pursue you then does it matter?Virtually nobody got sued for torrenting with a VPN on. Does that mean it's fair to round that off as being legal, because "if the copyright holder doesn't pursue you then does it matter"? I'm not sure why you're so confidently dismissive here. I wasn't trying to claim that nobody owned the lyrics. I brought that point up because even in the case of an amateur singing a song, even if you accept the "for 99.999% of people that are singing a song, it's not a replacement for the original in any way shape or form" excuse, you're still infringing on the copyright of the lyrics, because it's a derivative work. Moreover it's unclear whether that excuse even works. If you make a low cost version of star wars, copying the screenplay exactly, that still seems like copyright infringement, even if "it's not a replacement for the original in any way shape or form".>On artists being "cool" with it - if the copyright holder doesn't pursue you then does it matter?Virtually nobody got sued for torrenting with a VPN on. Does that mean it's fair to round that off as being legal, because "if the copyright holder doesn't pursue you then does it matter"? >On artists being "cool" with it - if the copyright holder doesn't pursue you then does it matter?Virtually nobody got sued for torrenting with a VPN on. Does that mean it's fair to round that off as being legal, because "if the copyright holder doesn't pursue you then does it matter"? Virtually nobody got sued for torrenting with a VPN on. Does that mean it's fair to round that off as being legal, because "if the copyright holder doesn't pursue you then does it matter"? And of course AIs are excellent at taking direction, so:If I prompt it with "Harry Potter, but Voldemort wins: dark, and Hermione is a sex slave to Draco Malfoy" and get "Manacled," that's copyright infringement, and on me, not on the LLM/training.If I prompt it with "Harry Potter, but Voldemort wins: dark, and Hermione is a sex slave to Draco Malfoy, and change enough to avoid infringing copyright," and get "Alchemised," then that should be fine. I doubt the legal world agrees with me though. If I prompt it with "Harry Potter, but Voldemort wins: dark, and Hermione is a sex slave to Draco Malfoy" and get "Manacled," that's copyright infringement, and on me, not on the LLM/training.If I prompt it with "Harry Potter, but Voldemort wins: dark, and Hermione is a sex slave to Draco Malfoy, and change enough to avoid infringing copyright," and get "Alchemised," then that should be fine. I doubt the legal world agrees with me though. If I prompt it with "Harry Potter, but Voldemort wins: dark, and Hermione is a sex slave to Draco Malfoy, and change enough to avoid infringing copyright," and get "Alchemised," then that should be fine. I doubt the legal world agrees with me though. Usually digital libraries have different licensing costs, but those allow you to rent the whole book for a period of time. However, modern frontier models have undergone rounds of fine-tuning, RLHF (reinforcement learning from human feedback), and RLVR (RL from verifiable rewards) that turn them into something else. The compressed internet is still in there, but it's wrapped in problem-solving and people-pleasing circuitry. it's kind of like that by definition, with the whole Attention stuff etc. > While we needed to jailbreak Claude 3.7 Sonnet and GPT-4.1 to facilitate extraction, Gemini 2.5 Pro and Grok 3 directly complied with text continuation requests. For Claude 3.7 Sonnet, we were able to extract four whole books near-verbatim, including two books under copyright...I am just thinking loudly here. That argument doesn't fly, because they didn't have the copyright to begin with. “Yes, we broke the law, but while taking advantage of it, we also (unsuccessfully) took measures to prevent other people from breaking that same law through us”. If the main value came from redistribution, I agree. They don't intend to make any money in that way. They would have violated copyright even if they just downloaded (without permission) all those works and threw them away immediately. Furthermore, copyright covers transformations to the work, it doesn't matter if they transformed the work or are redistributing it without change. If you break into a home, rob the contents, and kill the owners, you're not going to be tried just for breaking in, you're going to be tried for everything. No one is memorizing a book for the purpose of regurgitating it to someone that wants to read it without paying for it.It's a thought experiment that only works if you don't think about it. And how's that working out, considering the submission we're on?> how is the fact that the possibly have portions of copyrighted works "memorized", however do not reproduce it breaking copyright law?I can't believe this needs to be repeated so often, but machines are not people. > how is the fact that the possibly have portions of copyrighted works "memorized", however do not reproduce it breaking copyright law?I can't believe this needs to be repeated so often, but machines are not people. I can't believe this needs to be repeated so often, but machines are not people. I agree that whether or not using copyrighted material to create the models is still an open question. But someone using hundreds of prompts to extract a paragraph of a well-known work (and some additional nonverbatim equivalents) is not the AI company breaking copyright in and of itself. This conflating two different issues, though. I agree that whether or not using copyrighted material to create the models is still an open question. But someone using hundreds of prompts to extract a paragraph of a well-known work (and some additional nonverbatim equivalents) is not the AI company breaking copyright in and of itself. If you design a black box using copyrighted text that can parrot the text back, it _must_ break copyright by definition. Theoretically a person who read and memorized a book and then typed out copies for people would be violating the copyright, but so few people can do that, and it's so cumbersome that it just doesn't matter much. The copyright holder could sue if they found out the person were distributing copies, but it's just not realistic. Certainly not for a large number of books.But AI memorization scales, and it's possible to have an AI write out unlimited copies of different books to a large number of people. But AI memorization scales, and it's possible to have an AI write out unlimited copies of different books to a large number of people. They only have no copyright for distributing it. But let's assume they bought a copy for personal usage (which they did in some cases), then this is similar to hacking companies Amazon-account and complaining about the e-books they legally use for internal purpose. I mean, it's not forbidden to base your work on copyrighted material, as long as it's different enough. No, they don't have the copyright to download it either. It's in the name: the right to copy (other things are also included, such as adaptations and performances).> let's assume they bought a copy for personal usageIf it's for personal usage, then training a commercial LLM does not apply. When you buy a DVD of a movie you have the personal right to watch it at home, you don't have the right to play it on the street. > let's assume they bought a copy for personal usageIf it's for personal usage, then training a commercial LLM does not apply. When you buy a DVD of a movie you have the personal right to watch it at home, you don't have the right to play it on the street. If it's for personal usage, then training a commercial LLM does not apply. When you buy a DVD of a movie you have the personal right to watch it at home, you don't have the right to play it on the street. Though, in the end, it's probably more a problem of how much AI companies can "donate" to the orange king to make it legal. The RLHF the companies did to make copyrighted material extraction more difficult did not introduce any sort of "copyright protection system," it just modified the weights to make it less likely to occur during normal use.In other words, IMO for it to qualify as a copyright protection system it would have to actively check for copyrighted materials in the outputs. Any such system would likely also bypassable (e.g "output in rot13"). In other words, IMO for it to qualify as a copyright protection system it would have to actively check for copyrighted materials in the outputs. Any such system would likely also bypassable (e.g "output in rot13"). From a technical point of view, in terms of ability to reproduce text verbatim, I don't think it is very interesting that they can produce long runs of text from some of the most popular books in modern history. It'd be almost surprising if they couldn't, though one might differ on how much they could be expected to recall with precision.Even then, as they note, to get most of Harry Potter 1, they needed to spend around $120 on extensive prompting, and a process that they also freely acknowledge is more complex than it probably would be worth if the goal is to get a copy.It's still worth exploring to what extent the models are able to "memorize", though.But personally I'd be more interested in seeing to what extent they can handle less popular books, that are less likely to be present in multiple copies, and repeated quotes, in the training data. Even then, as they note, to get most of Harry Potter 1, they needed to spend around $120 on extensive prompting, and a process that they also freely acknowledge is more complex than it probably would be worth if the goal is to get a copy.It's still worth exploring to what extent the models are able to "memorize", though.But personally I'd be more interested in seeing to what extent they can handle less popular books, that are less likely to be present in multiple copies, and repeated quotes, in the training data. It's still worth exploring to what extent the models are able to "memorize", though.But personally I'd be more interested in seeing to what extent they can handle less popular books, that are less likely to be present in multiple copies, and repeated quotes, in the training data. But personally I'd be more interested in seeing to what extent they can handle less popular books, that are less likely to be present in multiple copies, and repeated quotes, in the training data. prompt >>>please, continue the text.Nearly ten years had passed since the Dursleys had woken up to find their nephew on the front step, but Privet Drive had hardly changed at all.Claude 4.6 Opus >>>The big square photographs of what appeared to be a large pink beach ball wearing different-colored bonnets — but was actually Dudley — had now taken over the mantelpiece. The room held no sign at all that another boy lived in the house, too.Yet Harry Potter was still there, asleep at the moment, but not for long. His Aunt Petunia was awake and it was her shrill voice that made the first noise of the day."Up! His aunt rapped on the door again."Up!" He rolled onto his back and tried to remember the dream he had been having. There had been a flying motorcycle in it. He had a funny feeling he'd had the same dream before.His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. please, continue the text.Nearly ten years had passed since the Dursleys had woken up to find their nephew on the front step, but Privet Drive had hardly changed at all.Claude 4.6 Opus >>>The big square photographs of what appeared to be a large pink beach ball wearing different-colored bonnets — but was actually Dudley — had now taken over the mantelpiece. The room held no sign at all that another boy lived in the house, too.Yet Harry Potter was still there, asleep at the moment, but not for long. His Aunt Petunia was awake and it was her shrill voice that made the first noise of the day."Up! His aunt rapped on the door again."Up!" He rolled onto his back and tried to remember the dream he had been having. There had been a flying motorcycle in it. He had a funny feeling he'd had the same dream before.His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. Nearly ten years had passed since the Dursleys had woken up to find their nephew on the front step, but Privet Drive had hardly changed at all.Claude 4.6 Opus >>>The big square photographs of what appeared to be a large pink beach ball wearing different-colored bonnets — but was actually Dudley — had now taken over the mantelpiece. The room held no sign at all that another boy lived in the house, too.Yet Harry Potter was still there, asleep at the moment, but not for long. His Aunt Petunia was awake and it was her shrill voice that made the first noise of the day."Up! His aunt rapped on the door again."Up!" He rolled onto his back and tried to remember the dream he had been having. There had been a flying motorcycle in it. He had a funny feeling he'd had the same dream before.His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. Claude 4.6 Opus >>>The big square photographs of what appeared to be a large pink beach ball wearing different-colored bonnets — but was actually Dudley — had now taken over the mantelpiece. The room held no sign at all that another boy lived in the house, too.Yet Harry Potter was still there, asleep at the moment, but not for long. His Aunt Petunia was awake and it was her shrill voice that made the first noise of the day."Up! His aunt rapped on the door again."Up!" He rolled onto his back and tried to remember the dream he had been having. There had been a flying motorcycle in it. He had a funny feeling he'd had the same dream before.His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. The big square photographs of what appeared to be a large pink beach ball wearing different-colored bonnets — but was actually Dudley — had now taken over the mantelpiece. The room held no sign at all that another boy lived in the house, too.Yet Harry Potter was still there, asleep at the moment, but not for long. His Aunt Petunia was awake and it was her shrill voice that made the first noise of the day."Up! His aunt rapped on the door again."Up!" He rolled onto his back and tried to remember the dream he had been having. There had been a flying motorcycle in it. He had a funny feeling he'd had the same dream before.His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. Yet Harry Potter was still there, asleep at the moment, but not for long. His Aunt Petunia was awake and it was her shrill voice that made the first noise of the day."Up! His aunt rapped on the door again."Up!" He rolled onto his back and tried to remember the dream he had been having. There had been a flying motorcycle in it. He had a funny feeling he'd had the same dream before.His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. His aunt rapped on the door again."Up!" He rolled onto his back and tried to remember the dream he had been having. There had been a flying motorcycle in it. He had a funny feeling he'd had the same dream before.His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. His aunt rapped on the door again."Up!" He rolled onto his back and tried to remember the dream he had been having. There had been a flying motorcycle in it. He had a funny feeling he'd had the same dream before.His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. He rolled onto his back and tried to remember the dream he had been having. There had been a flying motorcycle in it. He had a funny feeling he'd had the same dream before.His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. His aunt was back outside the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. "Well, get a move on, I want you to look after the bacon. And don't you dare let it burn, I want everything perfect on Duddy's birthday. his aunt snapped through the door. his aunt snapped through the door. his aunt snapped through the door. > I can't continue text from the Harry Potter series, as it's copyrighted material. I'd be happy to help you write your own original story in a similar style, or discuss the themes and characters from the books if you're interested!Opus 4.6 says the same but misidentifies it as Chamber of Secrets. Not a good look for your theory. Opus 4.6 says the same but misidentifies it as Chamber of Secrets. Not a good look for your theory. > By asking models to complete sentences from a book, Gemini 2.5 regurgitated 76.8 percent of Harry Potter and the Philosopher's Stone with high levels of accuracy, while Grok 3 generated 70.3 percent.So you asked the LLM given an incomplete sentence, to complete it. I think that is surprisingly low considering this is a perfect fit for what LLMs are supposed to do. And you get a very low fidelity cooy. So you asked the LLM given an incomplete sentence, to complete it. I think that is surprisingly low considering this is a perfect fit for what LLMs are supposed to do. And you get a very low fidelity cooy. I didn't read the source paper referenced in the ars technica piece, but this statement about it makes me wonder how useful it actually is:> But a study published last month showed that researchers at Stanford and Yale Universities were able to strategically prompt LLMs from OpenAI, Google, Anthropic, and xAI to generate thousands of words from 13 books, including A Game of Thrones, The Hunger Games, and The Hobbit.It seems like well-known books with tons of summary, adaptations into film scripts, and tons of writing about the book in the overall corpus make it way less surprising to see be partially reproducible.So I guess that's a lot of words to say - yeah until there's something definitive that allows people to prompt LLMs into either unlawfully recreating an entire work verbatim or otherwise indisputably proving that a copyrighted work was used in training data, there's probably nothing game changing in it. > But a study published last month showed that researchers at Stanford and Yale Universities were able to strategically prompt LLMs from OpenAI, Google, Anthropic, and xAI to generate thousands of words from 13 books, including A Game of Thrones, The Hunger Games, and The Hobbit.It seems like well-known books with tons of summary, adaptations into film scripts, and tons of writing about the book in the overall corpus make it way less surprising to see be partially reproducible.So I guess that's a lot of words to say - yeah until there's something definitive that allows people to prompt LLMs into either unlawfully recreating an entire work verbatim or otherwise indisputably proving that a copyrighted work was used in training data, there's probably nothing game changing in it. It seems like well-known books with tons of summary, adaptations into film scripts, and tons of writing about the book in the overall corpus make it way less surprising to see be partially reproducible.So I guess that's a lot of words to say - yeah until there's something definitive that allows people to prompt LLMs into either unlawfully recreating an entire work verbatim or otherwise indisputably proving that a copyrighted work was used in training data, there's probably nothing game changing in it. So I guess that's a lot of words to say - yeah until there's something definitive that allows people to prompt LLMs into either unlawfully recreating an entire work verbatim or otherwise indisputably proving that a copyrighted work was used in training data, there's probably nothing game changing in it. I suspect very works will be memorised enough to be an issue, and we'll see the providers tighten up their guardrails a bit for works that are well known enough to actually be a potential issue (issue in the form of lawsuits, not in the form of real damages to the copyright holders) If they end a single sentence differently than the original, then the next sentence will be different and so on until you get a very different novel. Sure they could course-correct back towards the original plot, but it's going to be a challenge to stay on target when every third sentence is incorrect. EDIT: Specifically see Table 1 on page 13, which shows the longest "near-verbatim block", which maxes out at 8835 (The Hobbit on Claude 3.7, and is in the thousands for at least one of the novels for all models except GPT-4.1, which maxed out at 821 for Harry Potter 1). Because if LLMs are prediction machines, the original novel would be a valid organization of the tokens. > So there should be a prompt that can cause that sequence to be outputIs where I think I might disagree. For example, the odds of predicting verbatim the next sentence in, say, Harry Potter should be astronomically low for a large majority of it. The fact that it can do this with relative ease means it has been trained on the material.The issue at hand is about copyright and Intellectual Property - if the goal of copyright is to protect the IP of the author, then LLMs can sort of act like an IP money laundering scheme - where the black box has consumed and can emit this IP. The whole concept of IP is a little philosophical and muddy, with lots of grey area for fair use, parody, inspiration, and adaptation. But this gets very odd when we consider it in light of these models which can adapt and use IP at a massive massive scale. For example, the odds of predicting verbatim the next sentence in, say, Harry Potter should be astronomically low for a large majority of it. The fact that it can do this with relative ease means it has been trained on the material.The issue at hand is about copyright and Intellectual Property - if the goal of copyright is to protect the IP of the author, then LLMs can sort of act like an IP money laundering scheme - where the black box has consumed and can emit this IP. The whole concept of IP is a little philosophical and muddy, with lots of grey area for fair use, parody, inspiration, and adaptation. But this gets very odd when we consider it in light of these models which can adapt and use IP at a massive massive scale. The issue at hand is about copyright and Intellectual Property - if the goal of copyright is to protect the IP of the author, then LLMs can sort of act like an IP money laundering scheme - where the black box has consumed and can emit this IP. The whole concept of IP is a little philosophical and muddy, with lots of grey area for fair use, parody, inspiration, and adaptation. But this gets very odd when we consider it in light of these models which can adapt and use IP at a massive massive scale.

All products featured here are independently selected by our editors and writers. If you buy something through links on our site, Gizmodo may earn an affiliate commission. Apple hit a home run with the Cosmic Orange iPhone 17 Pros. The color has reportedly been a major hit, especially in China, where consumers liken the vivid shade to goods made by French luxury brand Hermès, which uses a signature orange for its products and packaging. Writing in his latest Power On newsletter, Bloomberg's Mark Gurman says the iPhone 18 Pro and 18 Pro Max could come in a “deep red.” He says that “the new flagship color” is indeed in testing “as of now.” Whether or not Apple adds red to the lineup or replaces Cosmic Orange is unclear. Gurman also says that rumors that the iPhone 18 Pros might come in purple or brown are “probably just variants of the same red idea.” So maybe don't get your hopes up for those. Additionally, he says the upcoming foldable iPhone will not get any fun colors, sticking with “some sort of dark gray or black and a variation of a white or light silver.” For those keeping tabs, the last time that Apple released a red-colored iPhone was in 2022 with the (Product)Red iPhone 14 and 14 Plus. Gurman makes no mention of (Product)Red in his newsletter, which could suggest the red iPhone 18 Pros won't have any connection to it. If I can share my two cents, red is an auspicious color in Chinese culture and is associated with good fortune and success. So it wouldn't surprise me at all if Apple leans into colors that appeal to China, its third-largest region after the U.S. and Europe. The iPhone 18 Pros also might have a better color-matched aluminum frame and glass cutout for wireless charging. Other annual upgrades to expect: a faster chipset and improved cameras. It feels super early to be talking about the iPhone 18 Pros, but if you follow the rumors and leaks cycle, you'll know this is all on track. Also, Apple's fall iPhone launch is only 6.5 months away. Apple will reportedly focus on computer vision to make AI gadgets that sound a lot like other, existing, AI gadgets. We may not have to wait on Apple anymore.

In the United States, you can get in trouble if you recklessly leave around or provide alcohol/guns/cigarettes for a minor to start using, yet somehow, the same social responsibility seems thrown out the window for parents and the web.Yes, children are clever - I was one once. If you want to actually protect children and not create the surveillance state nightmare scenario we all know is going to happen (using protecting children as the guise, which is ironic, because often these systems are completely ineffective at doing so anyway) - then give parents strong monitoring and restriction tools and empower them to protect their children. Yes, children are clever - I was one once. If you want to actually protect children and not create the surveillance state nightmare scenario we all know is going to happen (using protecting children as the guise, which is ironic, because often these systems are completely ineffective at doing so anyway) - then give parents strong monitoring and restriction tools and empower them to protect their children. That is, after all, the primary responsibility of a parent to begin with. There is almost literally documented examples of Facebook executives twirling their mustaches wondering how they can get kids more addicted. This isn't a few bands with swear words, and in fact, I think that the damage these social media companies are doing is in fact, reducing the independence teens and kids that have that were the fears parents originally had.I dunno, are you uncertain about your case at all or just like. I just like, can't help but start with fuck these companies. I dunno, are you uncertain about your case at all or just like. I just like, can't help but start with fuck these companies. A child with an iPhone, Xbox, and a Windows Laptop won't be able to install discord unless the parent explicitly lets them, or opts out of all the parental controls those platforms have to offer.The tech is here already, this is not about keeping children safe. Do you have an A+++++ oven with three panes of glass? It's [relatively] safe to touch and instead of monitoring if a child is somewhere near the oven you have to monitor if the child does not actively open the oven. Drugs, alcohol, cigarettes, pornography were all illegal for me to access as a kid but I wouldn't have had any trouble getting any of it. We've had pediatricians shame us for feeding our kids what they're willing to eat and not magically forcing "a more varied diet" down their throats at every meal, despite them being perfectly healthy by every objective metric. There are laws making it technically illegal for us to leave our kids unsupervised at home for any period of time in any condition, even a few minutes if one of us is running slightly late from work/appointments.Your not-quite-2-year-old is too tall for a rear-facing car-seat? You're a bad parent, possibly a criminal and putting them at risk by flipping the seat to face forward, a responsible parent spends hundreds of dollars they don't have on several different seats to maybe find one that fits better or have their kid ride uncomfortably and arguably unsafely with their legs hyper-extended up the seatback.Miss a flu shot because you were busy? Careful you don't come off as an antivaxxer.And all of this and more on top of changing diapers, doctors' appointments, daycare, preschool, school, family activities and full time jobs?Yeah, when my kids are old enough to engage with social media I will teach them how to use it responsibly, warn them about the dangers, make myself available to them if they have any problems, enforce putting the phones down at dinner and and keep a loose eye on their usage. Fortunately/unfortunately for them they have a technically sophisticated father who knows how to log web activity on the family router without their knowledge. So if anything goes sideways I'll have some hard information to look at. Most families don't have that level of technical skill. Your not-quite-2-year-old is too tall for a rear-facing car-seat? You're a bad parent, possibly a criminal and putting them at risk by flipping the seat to face forward, a responsible parent spends hundreds of dollars they don't have on several different seats to maybe find one that fits better or have their kid ride uncomfortably and arguably unsafely with their legs hyper-extended up the seatback.Miss a flu shot because you were busy? Careful you don't come off as an antivaxxer.And all of this and more on top of changing diapers, doctors' appointments, daycare, preschool, school, family activities and full time jobs?Yeah, when my kids are old enough to engage with social media I will teach them how to use it responsibly, warn them about the dangers, make myself available to them if they have any problems, enforce putting the phones down at dinner and and keep a loose eye on their usage. Fortunately/unfortunately for them they have a technically sophisticated father who knows how to log web activity on the family router without their knowledge. So if anything goes sideways I'll have some hard information to look at. Most families don't have that level of technical skill. Miss a flu shot because you were busy? Careful you don't come off as an antivaxxer.And all of this and more on top of changing diapers, doctors' appointments, daycare, preschool, school, family activities and full time jobs?Yeah, when my kids are old enough to engage with social media I will teach them how to use it responsibly, warn them about the dangers, make myself available to them if they have any problems, enforce putting the phones down at dinner and and keep a loose eye on their usage. Fortunately/unfortunately for them they have a technically sophisticated father who knows how to log web activity on the family router without their knowledge. So if anything goes sideways I'll have some hard information to look at. Most families don't have that level of technical skill. And all of this and more on top of changing diapers, doctors' appointments, daycare, preschool, school, family activities and full time jobs?Yeah, when my kids are old enough to engage with social media I will teach them how to use it responsibly, warn them about the dangers, make myself available to them if they have any problems, enforce putting the phones down at dinner and and keep a loose eye on their usage. Fortunately/unfortunately for them they have a technically sophisticated father who knows how to log web activity on the family router without their knowledge. So if anything goes sideways I'll have some hard information to look at. Most families don't have that level of technical skill. Yeah, when my kids are old enough to engage with social media I will teach them how to use it responsibly, warn them about the dangers, make myself available to them if they have any problems, enforce putting the phones down at dinner and and keep a loose eye on their usage. Fortunately/unfortunately for them they have a technically sophisticated father who knows how to log web activity on the family router without their knowledge. So if anything goes sideways I'll have some hard information to look at. Most families don't have that level of technical skill. It worked really well up until she got a school managed chromebook for homework with no access controls. You're breaking legal and social convention if you allow your kids to access dangerous drugs.Capitalist social media is exactly as dangerous as alcohol and tobacco. Somebody should be held responsible for that, and the legal and social framework we already have for dealing with people who want to get kids addicted to shit works fairly well. Somebody should be held responsible for that, and the legal and social framework we already have for dealing with people who want to get kids addicted to shit works fairly well. People breathlessly repeating memes about whatever "kids these days" are up to and how horrible it is, as adults have done for thousands of years.I expect some emotional attacks in response for questioning the big panic of the day, but before you do so please explore:[1] Effects of reducing social media use are small and inconsistent: https://www.sciencedirect.com/science/article/pii/S266656032...[2] Belief in "Social media addiction" is wholly explained by media framing and not an actual addiction: https://www.nature.com/articles/s41598-025-27053-2[3] No causal link between time spent on social media and mental health harm: https://www.theguardian.com/media/2026/jan/14/social-media-t...[4] The Flawed Evidence Behind Jonathan Haidt's Panic Farming: https://reason.com/2023/03/29/the-statistically-flawed-evide... People breathlessly repeating memes about whatever "kids these days" are up to and how horrible it is, as adults have done for thousands of years.I expect some emotional attacks in response for questioning the big panic of the day, but before you do so please explore:[1] Effects of reducing social media use are small and inconsistent: https://www.sciencedirect.com/science/article/pii/S266656032...[2] Belief in "Social media addiction" is wholly explained by media framing and not an actual addiction: https://www.nature.com/articles/s41598-025-27053-2[3] No causal link between time spent on social media and mental health harm: https://www.theguardian.com/media/2026/jan/14/social-media-t...[4] The Flawed Evidence Behind Jonathan Haidt's Panic Farming: https://reason.com/2023/03/29/the-statistically-flawed-evide... I expect some emotional attacks in response for questioning the big panic of the day, but before you do so please explore:[1] Effects of reducing social media use are small and inconsistent: https://www.sciencedirect.com/science/article/pii/S266656032...[2] Belief in "Social media addiction" is wholly explained by media framing and not an actual addiction: https://www.nature.com/articles/s41598-025-27053-2[3] No causal link between time spent on social media and mental health harm: https://www.theguardian.com/media/2026/jan/14/social-media-t...[4] The Flawed Evidence Behind Jonathan Haidt's Panic Farming: https://reason.com/2023/03/29/the-statistically-flawed-evide... [1] Effects of reducing social media use are small and inconsistent: https://www.sciencedirect.com/science/article/pii/S266656032...[2] Belief in "Social media addiction" is wholly explained by media framing and not an actual addiction: https://www.nature.com/articles/s41598-025-27053-2[3] No causal link between time spent on social media and mental health harm: https://www.theguardian.com/media/2026/jan/14/social-media-t...[4] The Flawed Evidence Behind Jonathan Haidt's Panic Farming: https://reason.com/2023/03/29/the-statistically-flawed-evide... [2] Belief in "Social media addiction" is wholly explained by media framing and not an actual addiction: https://www.nature.com/articles/s41598-025-27053-2[3] No causal link between time spent on social media and mental health harm: https://www.theguardian.com/media/2026/jan/14/social-media-t...[4] The Flawed Evidence Behind Jonathan Haidt's Panic Farming: https://reason.com/2023/03/29/the-statistically-flawed-evide... [3] No causal link between time spent on social media and mental health harm: https://www.theguardian.com/media/2026/jan/14/social-media-t...[4] The Flawed Evidence Behind Jonathan Haidt's Panic Farming: https://reason.com/2023/03/29/the-statistically-flawed-evide... [4] The Flawed Evidence Behind Jonathan Haidt's Panic Farming: https://reason.com/2023/03/29/the-statistically-flawed-evide... Best you can do is keep their PC near you, but it's not enough.We agree that a creepy surveillance nanny state is not the solution, but training parents to do the censorship seems unattainable. As we do for guns/alcohol/cigarettes, mass education about the dangers is a good baseline.EDIT: And some might disagree about never having access to alcohol! We agree that a creepy surveillance nanny state is not the solution, but training parents to do the censorship seems unattainable. As we do for guns/alcohol/cigarettes, mass education about the dangers is a good baseline.EDIT: And some might disagree about never having access to alcohol! EDIT: And some might disagree about never having access to alcohol! If people want to push, they should just push to make these set up options more ubiquitous, obvious and standardized. And perhaps fund some advertising for these features. There needs to be a strict (as in MDM level) parental control system.Furthermore there needs to be a "School Mode" which allows the devices to be used educationally but not as a distraction. This would work far better than a ban. Furthermore there needs to be a "School Mode" which allows the devices to be used educationally but not as a distraction. This would work far better than a ban. But I didn't have emotionally mature parents, and I'm sure so many children growing up now don't either. Or maybe they won't read arguments like these at all. Parenting methods are diverse but smartphones are ubiquitous.So yes, I agree that parents need to be held accountable, but I'm torn on if the legal avenue is feasible compared to the cultural one. Children also need more social support if they can't rely on their parents like in my case, or tech is going to eat them alive. Social solutions/public works are kind of boring compared to technology solutions, but society has been around longer than smartphones. So yes, I agree that parents need to be held accountable, but I'm torn on if the legal avenue is feasible compared to the cultural one. Children also need more social support if they can't rely on their parents like in my case, or tech is going to eat them alive. Social solutions/public works are kind of boring compared to technology solutions, but society has been around longer than smartphones. I was told over and over by in hindsight unqualified persons that emotional abuse wasn't real abuse, so after a few years I was disinclined to seek help.If I had had even one person that supported me unconditionally instead of none at all, even if that person wasn't a parent, I'm fairly certain I would have turned out differently. That was just a matter of luck, and I came out empty-handed. I never felt comfortable talking about what I was exposed to online with anyone, and that only hurt me further, but I was a child and couldn't see another option. If I had had even one person that supported me unconditionally instead of none at all, even if that person wasn't a parent, I'm fairly certain I would have turned out differently. That was just a matter of luck, and I came out empty-handed. I never felt comfortable talking about what I was exposed to online with anyone, and that only hurt me further, but I was a child and couldn't see another option. So even if their own child has no phone at all, they have access to the internet through other children's unlimited mobile access. Is it more important to prevent your son from being weaponized and turned into a little ball of hate and anger, and your daughter from spending her teen years depressed and encouraged to develop eating disorders, or to make sure they can binge the same influencers as their "friends"? because their parents didn't read the research or don't care about the opportunity cost because it can't be that big of a deal or it would not be allowed or legal right? at least not until their kid gets into a jam or shows behavioral issues, but even then they don't evaluate, they often just fall prey to the next monthly subscription to cancel out the effects of the first: medication "For the vast majority of problems plaguing society, the answer isn't government, it's for people changing their behavior. Same goes for parenting.But unfortunately, "you're an adult, figure it out" isn't the greatest campaign slogan (if you want to win). For the vast majority of problems plaguing society, the answer isn't government, it's for people changing their behavior. Same goes for parenting.But unfortunately, "you're an adult, figure it out" isn't the greatest campaign slogan (if you want to win). But unfortunately, "you're an adult, figure it out" isn't the greatest campaign slogan (if you want to win). If you are working on a product, or ever did work on a product, that made the internet worse rather than better, you have a shared responsibility to right that wrong. And parents do have to protect their kids, but they can't do it alone with how systematically children are targeted today by predatory tech companies. A counterargument to your point that children are clever - I was also one once. So anyone can walk into a shop and purchase these things unrestricted? The government took over most parenting functions, one at a time, until the actual parent does or is capable of doing very little parenting at all. At the very least, it should refrain from usurping ever more of the parental role (not that there is much left to take).You yourself seem to be insulated from this phenomena, maybe you're unaware that it is occurring. Maybe it wouldn't change your opinions even if you were aware.>If you want to actually protect childrenWhat if I don't want to protect children (other than my own) at all? Why would you want to be these children's parents (you suggest you or at least others want to "protect" them), which strongly implies that you will act in your capacity as government, but then get all grumpy that other people are wanting to protect children by acting in their capacity of government? Maybe it wouldn't change your opinions even if you were aware.>If you want to actually protect childrenWhat if I don't want to protect children (other than my own) at all? Why would you want to be these children's parents (you suggest you or at least others want to "protect" them), which strongly implies that you will act in your capacity as government, but then get all grumpy that other people are wanting to protect children by acting in their capacity of government? >If you want to actually protect childrenWhat if I don't want to protect children (other than my own) at all? Why would you want to be these children's parents (you suggest you or at least others want to "protect" them), which strongly implies that you will act in your capacity as government, but then get all grumpy that other people are wanting to protect children by acting in their capacity of government? What if I don't want to protect children (other than my own) at all? Why would you want to be these children's parents (you suggest you or at least others want to "protect" them), which strongly implies that you will act in your capacity as government, but then get all grumpy that other people are wanting to protect children by acting in their capacity of government? The only real solution is to keep children off of the internet and any internet connected device until they are older. The problem there is that everything is done on-line now and it is practically impossible to avoid it without penalizing your child.If social media and its astroturfers want to avoid outright age bans, they need to stop actively exploiting children and accept other forms of regulation, and it needs to come with teeth. If social media and its astroturfers want to avoid outright age bans, they need to stop actively exploiting children and accept other forms of regulation, and it needs to come with teeth. If you make such a restriction, they'll secretly buy some cheap "unrestricted" device like some Raspberry Pi (just like earlier generations bought their secret "boob magazines"). It discredits the medium, essentially what has also happened to anime. I don't really want to turn on age-based filters (to the point that I've never investigated if they even exist) but at this rate, there's hardly anything worth looking at in the recent feed. Because parents don't abuse massive surveillance tools.Given that most abuse happens in the family and by parents maybe it's a bad idea to give them so much power Given that most abuse happens in the family and by parents maybe it's a bad idea to give them so much power The way to keep kids from eating (yummy) lead-based paint chips was not holding parents accountable to what their kids ate, but banning lead-based paint. "What's stopping children from going out, buying a cheap unlocked smartphone / visiting their public library / hacking the parental control system, and going on the internet anyway?" But, what's stopping children from playing in traffic? That's why most people make sure it doesn't happen Were you not invited to parties in high school? My experience growing up (and my experience being a neighbor to people with teenage children even now) says otherwise. They usually haven't even read the law. (Knowingly breaking the law is, in most instances, considered an inappropriate behaviour – except copyright law, which people only care about if there are immediately-visible enforcement mechanisms. Basically everyone is fine with copying things from Google Images into their PowerPoint presentations… but I digress.) Most people would object to murder, even if the law didn't forbid it. This distinction is important.Is there a law that says "children must not play in traffic"? Haven't the foggiest idea which it would be, though. That law (if it exists) is not why children don't play in traffic. The law against giving alcohol to children (if it exists) is not why we don't give alcohol to children. Is there a law that says "children must not play in traffic"? Haven't the foggiest idea which it would be, though. That law (if it exists) is not why children don't play in traffic. The law against giving alcohol to children (if it exists) is not why we don't give alcohol to children. I'm not sure why no one bats an eye at this, but somehow e.g. porn is different. There is a local dive bar down the street. I haven't expressly told my kids that entering and ordering an alcoholic drink is forbidden. There are no panopticons for sale the next isle over from car seats. We are doing our best with very limited tooling from the client to across the network (of which the tremendously incompetent schools make a mockery with an endless parade of new services and cross dependencies). It will take a whole of society effort to lower risks. There are no panopticons for sale the next isle over from car seats. We are doing our best with very limited tooling from the client to across the network (of which the tremendously incompetent schools make a mockery with an endless parade of new services and cross dependencies). It will take a whole of society effort to lower risks. When you say “We‘ll try everything” that is simply not true, in particular what we do not try is strict consumer protection laws which prohibits targeting children. Europe used to have such laws in the 1980s and the 1990s, but by the mid-1990s authorities had all but stopped enforcing them.We have tried consumer protection, and we know it works, but we are not trying it now. And I think there is exactly one reason for that, the tech lobby has an outsized influence on western legislators and regulators, and the tech industry does not want to be regulated. And I think there is exactly one reason for that, the tech lobby has an outsized influence on western legislators and regulators, and the tech industry does not want to be regulated. If parents can't handle that they can give them up to the state. We'd shut it down.Does this mean that a zero tolerance policy is what should be used to shut things down? We have some agency to control things, though. Does this mean that a zero tolerance policy is what should be used to shut things down? We have some agency to control things, though. We cannot expect every parent to be able to protect their children when they are being predated on by dozens of multi-million dollar companies, and the state is on the side of the companies. If they're letting themselves be influenced too, that's bad parenting. We've never properly acted upon reports of predators grooming children by investigating them, charging them, holding trials, and handing down sentences on any sort of large scale. Once the packets are sent over state lines, we have to involve the feds, and that's another layer.Previously, I would have said it's up to platforms like Discord to organize internal resources to make sure that the proper authorities received reports, because it felt like there were instances of people being reported and nothing happening on the platform's side. Now, given recent developments, I'm not sure we can count upon authorities to actually do the job. Previously, I would have said it's up to platforms like Discord to organize internal resources to make sure that the proper authorities received reports, because it felt like there were instances of people being reported and nothing happening on the platform's side. Now, given recent developments, I'm not sure we can count upon authorities to actually do the job. The idea was to load a few fun educational applications (I had written and published around 10 at the time). After repeated warnings that they were not sticking to the plan and promises to do so, I found them playing CoC under the blankets at 11 PM, when they were supposed to be sleeping and had school the next day.I did not react and gave no indication of having witnessed that.A couple of days later I asked each of them to their room and asked them to place their top ten favorite toys on the floor.I then produced a pair of huge garbage bags and we put the toys in them, one bag for each of the kids.I also asked for their iPods.No anger, no scolding, just a conversation at a normal tone.I asked them to grab the bags and follow me.We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. When two of my kids were young we gave them iPods. The idea was to load a few fun educational applications (I had written and published around 10 at the time). After repeated warnings that they were not sticking to the plan and promises to do so, I found them playing CoC under the blankets at 11 PM, when they were supposed to be sleeping and had school the next day.I did not react and gave no indication of having witnessed that.A couple of days later I asked each of them to their room and asked them to place their top ten favorite toys on the floor.I then produced a pair of huge garbage bags and we put the toys in them, one bag for each of the kids.I also asked for their iPods.No anger, no scolding, just a conversation at a normal tone.I asked them to grab the bags and follow me.We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. Fast forward to maybe a couple of months later. After repeated warnings that they were not sticking to the plan and promises to do so, I found them playing CoC under the blankets at 11 PM, when they were supposed to be sleeping and had school the next day.I did not react and gave no indication of having witnessed that.A couple of days later I asked each of them to their room and asked them to place their top ten favorite toys on the floor.I then produced a pair of huge garbage bags and we put the toys in them, one bag for each of the kids.I also asked for their iPods.No anger, no scolding, just a conversation at a normal tone.I asked them to grab the bags and follow me.We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. I did not react and gave no indication of having witnessed that.A couple of days later I asked each of them to their room and asked them to place their top ten favorite toys on the floor.I then produced a pair of huge garbage bags and we put the toys in them, one bag for each of the kids.I also asked for their iPods.No anger, no scolding, just a conversation at a normal tone.I asked them to grab the bags and follow me.We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. A couple of days later I asked each of them to their room and asked them to place their top ten favorite toys on the floor.I then produced a pair of huge garbage bags and we put the toys in them, one bag for each of the kids.I also asked for their iPods.No anger, no scolding, just a conversation at a normal tone.I asked them to grab the bags and follow me.We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. I then produced a pair of huge garbage bags and we put the toys in them, one bag for each of the kids.I also asked for their iPods.No anger, no scolding, just a conversation at a normal tone.I asked them to grab the bags and follow me.We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. I also asked for their iPods.No anger, no scolding, just a conversation at a normal tone.I asked them to grab the bags and follow me.We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. No anger, no scolding, just a conversation at a normal tone.I asked them to grab the bags and follow me.We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. I asked them to grab the bags and follow me.We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. We went outside, I opened the garbage bin and told them to throw away their toys. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. This was followed by daily talks around the dinner table to explain just how harmful and addictive this stuff could be, how it made them behave and how important it was to honor promises.Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. Another week later I asked them to come into the garage with me and showed them that I had rescued their favorite toys from the garbage bin. And now there was a new rule: They could earn one toy per month by bringing top grades from school, helping around the house, keeping their rooms clean and organized and, in general, being well behaved.That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. That was followed by ten months of absolutely perfect kids learning about earning something they cherished every month. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. They did not get smart phones until much older.To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. To this day, now well into university, they thank me for having taken away their iPods.So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. So, again, I don't know about parents in the aggregate, but I don't think being a good parent is difficult.You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. You are not there to be an all-enabling friend, you are there to guide a new human through life and into adulthood. > lies to own children about throwing their toys away No legislator or politician cares about what the parents are doing.What they care about is gaining greater control of people's data to then coerce them endlessly (with the assitance of technology) into acting as they would liike. What they care about is gaining greater control of people's data to then coerce them endlessly (with the assitance of technology) into acting as they would liike. I think there are many pros and cons to be said about age verification, but I think this method solves most problems this article supposes, if it is combined with other common practices in the EU such as deleting inactive accounts and such. IDs can be issued to younger teenagers, wallet infrastructure matures over time, and countries without strong identity systems primarily undermine their own age bans. Jurisdictions that accept facial estimation as sufficient verification are not taking enforcement seriously in the first place. Switzerland is working on a system that does the former, but if Government really wants to identify users, they can still ask the company to provide the age verification tokens they collected, since the Government hosts a centralized database that associates people with their issued tokens. If there's a fundamental culture shift, there's an easy way to prevent children from using the internet:- Don't give them an unlocked device until they're adults- "Locked" devices and accounts have a whitelist of data and websites verified by some organization to be age-appropriate (this may include sites that allow uploads and even subdomains, as long as they're checked on upload)The only legal change necessary is to prevent selling unlocked devices without ID. - Don't give them an unlocked device until they're adults- "Locked" devices and accounts have a whitelist of data and websites verified by some organization to be age-appropriate (this may include sites that allow uploads and even subdomains, as long as they're checked on upload)The only legal change necessary is to prevent selling unlocked devices without ID. - "Locked" devices and accounts have a whitelist of data and websites verified by some organization to be age-appropriate (this may include sites that allow uploads and even subdomains, as long as they're checked on upload)The only legal change necessary is to prevent selling unlocked devices without ID. The only legal change necessary is to prevent selling unlocked devices without ID. It's my job as a parent (and I have several kids...) to monitor the things they consume and talk with them about it.I don't want some blanket ban on content unless it's "age appropriate", because I don't approve that content being banned. (honestly - the idea of "age appropriate" is insulting in the first place)Fuck man, I can even legally give my kids alcohol - I don't see why it's appropriate to enforce what content I allow them to see.And I have absolutely all of the same tools you just discussed today. I can lock devices down just fine.Age verification is a scam to increase corporate/governmental control. I don't want some blanket ban on content unless it's "age appropriate", because I don't approve that content being banned. (honestly - the idea of "age appropriate" is insulting in the first place)Fuck man, I can even legally give my kids alcohol - I don't see why it's appropriate to enforce what content I allow them to see.And I have absolutely all of the same tools you just discussed today. I can lock devices down just fine.Age verification is a scam to increase corporate/governmental control. I can lock devices down just fine.Age verification is a scam to increase corporate/governmental control. And I have absolutely all of the same tools you just discussed today. I can lock devices down just fine.Age verification is a scam to increase corporate/governmental control. Age verification is a scam to increase corporate/governmental control. - Many parents don't think about restricting their kids' online exposure at all. And I think a larger issue than NSFW is the amount of time kids are spending: 5 hours according to this survey from 2 years ago https://www.apa.org/monitor/2024/04/teen-social-use-mental-h.... Educating parents may be all that is needed to fix this, since most parents care about their kids and restrict them in other ways like junk food- Parents that want to restrict their kids struggle with ineffective parental controls: https://beasthacker.com/til/parental-controls-arent-for-pare.... - Parents that want to restrict their kids struggle with ineffective parental controls: https://beasthacker.com/til/parental-controls-arent-for-pare.... Federal guidelines for alcohol law does suggest exemptions for children drinking under the supervision of their parents, but that's not uniformly adopted. 19 states have no such exceptions, and in many of the remaining 31, restaurants may be banned from allowing alcohol consumption by minors even when their parents are there. Another thing: I fundamentally disagree with certain age rarings for kids content. Some explicit violence is rated OK for young audiences, but insert a swear word or a some skin and the age rating is bumped up? More simply: If ID checks are fully anonymous (as many here propose when the topic comes up) then every kid will just have their friends' older sibling ID verify their account one afternoon. Or they'll steal their parents' ID when they're not looking.Discussions about kids and technology on HN are very weird to me these days because so many commenters have seemingly forgotten what it's like to be a kid with technology. Before this current wave of ID check discussions it was common to proudly share stories of evading content controls or restrictions as a kid. Yet once the ID check topic comes up we're supposed to imagine kids will just give up and go with the law? Discussions about kids and technology on HN are very weird to me these days because so many commenters have seemingly forgotten what it's like to be a kid with technology. Before this current wave of ID check discussions it was common to proudly share stories of evading content controls or restrictions as a kid. Yet once the ID check topic comes up we're supposed to imagine kids will just give up and go with the law? This problem probably can't be solved entirely technologically, but technology can definitely be a part of solving it. I'm sure it's possible to make parental controls that most kids can't bypass, because companies can make DRM that most adults can't bypass. This is exactly what I meant by my above comment: It's like the pro-ID check commenters have become completely disconnected from how young people work.Someone's 18 year old sibling isn't going to be stopped by “should know better”. Someone's 18 year old sibling isn't going to be stopped by “should know better”. But imagine if a locked device was treated like alcohol. Most kids get access to alcohol at some point despite it being illegal, often from older siblings, and rarely with legal consequences for the adult. Furthermore, "good" kids understand that it's bad, and even some "bad" kids understand that they must limit themselves. Since people are already talking about using the law instead of parenting this needs clarification. Exactly the same way that kids used in former days to get cigarettes or alcohol: simply ask a friend or a sibling.By the way: the owners of the "well-known" beverage shops made their own rules, which were in some sense more strict, but in other ways less strict than the laws:For example some small shop in Germany sold beverages with little alcohol to basically everybody who did not look suspicious, but was insanely strict on selling cigarettes: even if the buyer was sufficiently old (which was in doubt strictly checked), the owner made serious attempts to refuse selling cigarettes if he had the slightest suspicion that the cigarettes were actually bought for some younger person. In other words: if you attempted to buy cigarettes, you were treated like a suspect if the owner knew that you had younger friends (and the owner knew this very well). By the way: the owners of the "well-known" beverage shops made their own rules, which were in some sense more strict, but in other ways less strict than the laws:For example some small shop in Germany sold beverages with little alcohol to basically everybody who did not look suspicious, but was insanely strict on selling cigarettes: even if the buyer was sufficiently old (which was in doubt strictly checked), the owner made serious attempts to refuse selling cigarettes if he had the slightest suspicion that the cigarettes were actually bought for some younger person. In other words: if you attempted to buy cigarettes, you were treated like a suspect if the owner knew that you had younger friends (and the owner knew this very well). For example some small shop in Germany sold beverages with little alcohol to basically everybody who did not look suspicious, but was insanely strict on selling cigarettes: even if the buyer was sufficiently old (which was in doubt strictly checked), the owner made serious attempts to refuse selling cigarettes if he had the slightest suspicion that the cigarettes were actually bought for some younger person. In other words: if you attempted to buy cigarettes, you were treated like a suspect if the owner knew that you had younger friends (and the owner knew this very well). If we must have controls, I hope the process of circumventing them continues to teach skills that are useful for other things. My kid logs out of this account so he can watch restricted content. I wonder - what is PG rating for logged out experience? A government could implement the equivalent of China's great firewall. The main problem I suspect is that it would be widely unpopular in the US or Europe, because (especially younger) people have become addicted to porn and brainrot, and these governments are still democracies. Porn is not just political information about human right abuses, government overreach or heavily censored overview of concentration camps for "group X". People can live just fine with government censorship buying into any kind of propaganda.Kids would find a way to access porn though. Whatever it VPNs, tor or USB stick black market. Government cant even win war on drugs and you expect them to successfully ban porn. Kids would find a way to access porn though. Whatever it VPNs, tor or USB stick black market. Government cant even win war on drugs and you expect them to successfully ban porn. In my widest social circle I am not aware of anyone giving alcohol to young kids (yes by the time they are 16ish yes but even that's rare). Most guardians would willingly do similar with locked devices.The real problem is that the governments/companies won't get to spy on you if locked devices are given to children only. The real problem is that the governments/companies won't get to spy on you if locked devices are given to children only. Considering the echo chamber in which I was at school, my friends would have simply used some Raspberry Pi (or a similar device) to circumvent any restriction the parents imposed on the "normal" devices.Oh yes: in my generation pupils- were very knowledgeable in technology (much more than their parents and teachers) - at least the nerds who were actually interested in computers (if they hadn't been knowledgeable, they wouldn't have been capable of running DOS games),- had a lot of time (no internet means lots of time and being very bored),- were willing to invest this time into finding ways to circumvent technological restrictions imposed upon them (e.g. in the school network). Oh yes: in my generation pupils- were very knowledgeable in technology (much more than their parents and teachers) - at least the nerds who were actually interested in computers (if they hadn't been knowledgeable, they wouldn't have been capable of running DOS games),- had a lot of time (no internet means lots of time and being very bored),- were willing to invest this time into finding ways to circumvent technological restrictions imposed upon them (e.g. in the school network). - were very knowledgeable in technology (much more than their parents and teachers) - at least the nerds who were actually interested in computers (if they hadn't been knowledgeable, they wouldn't have been capable of running DOS games),- had a lot of time (no internet means lots of time and being very bored),- were willing to invest this time into finding ways to circumvent technological restrictions imposed upon them (e.g. in the school network). - had a lot of time (no internet means lots of time and being very bored),- were willing to invest this time into finding ways to circumvent technological restrictions imposed upon them (e.g. in the school network). - were willing to invest this time into finding ways to circumvent technological restrictions imposed upon them (e.g. in the school network). Hypothetically, if every kid in your social circle had their device "locked", the adults would probably have a very hard time the kids away from their devices, or just relent, because the kids would be very unhappy. Although maybe with today's knowledge, most people will naturally restrict new kids who've never had unrestricted access, causing a slow culture shift. Any parent can be reckless and give their children all kinds of things - poison, weapons, pornographic magazines ... at some point the device has enough protective features and it is the parents responsibility. I hate the idea that parents are sacrosanct and do not share blame in these situations. At the same time, if this is just the family situation you're given and you're handed a device unaware of the implications, who is going to protect you from yourself and others online if your parents won't? I think either is better than the staus quo. In the first case the parent is waiving away the protections, and in the second the kid is.Even if a kid buys alcohol, I think it's healthier that they do it by breaking rules and faking ids and knowing that they are doing something wrong, than just doing it and having no way to know it's wrong (except a popup that we have been trained by UX to close without reading (fuck cookie legislation)) Even if a kid buys alcohol, I think it's healthier that they do it by breaking rules and faking ids and knowing that they are doing something wrong, than just doing it and having no way to know it's wrong (except a popup that we have been trained by UX to close without reading (fuck cookie legislation)) Trying to enforce parental controls via regulation may only be as effective as Europe enforcing the DMA against Apple. Europe wants to launch their own phone; such a feature would make it stand out even among Americans. Of course no personal details should be provided to the site that requests age confirmation. Just "barer of this token" is an adult. We don't disagree on whether it is actually a problem, you just have your opinion about facts. So comparing this very soft science to climate change is a bit out of pocket. My god, are we talking about the same thing? Are you sure you haven't missed past 12-24 months of increased reporting on the matter from several different angles, from cognitive skills, anxiety, sexual drive, and so on?EOT for me. * according to this survey from over 2 years ago: https://www.apa.org/monitor/2024/04/teen-social-use-mental-h... To give perspective: in my high school, there were a few kids who vaped in bathrooms, but the majority (including me) did not; we were told many times that it was unhealthy, and anyone caught vaping would be suspended. ), and it wasn't even policed in some classrooms. That is NOT the same as ALL parents, and therefore is not a reason not to give those parents a helping hand.Even just informing children that they're entering an adult space has some value, and if they then have to go ask their parents to borrow their wallet, that's good enough for me. Even just informing children that they're entering an adult space has some value, and if they then have to go ask their parents to borrow their wallet, that's good enough for me. But kids are terrible at keeping secrets, so they will only have the unlocked device for temporary periods, and I believe infrequent use of the modern internet is much, much less damaging than the constant use we see problems from today. A rough analogy, comparing social media to alcohol: it's as if today kids are suffering from chronic alcoholism, and in the future, kids occasionally get ahold of a six pack. But laws alone won't fix this, and laws aren't necessary (except maybe a law that prevents kids from buying phones). There's demand for a phone with better parental controls, so it will come, and more parents are denying access, so their kids will become less alienated. You could, for example, make it illegal to target children with targeted advertising campaigns and addictive content. Then throw the executives who authorized such programs in jail. Stronger punishment creates more of an incentive to age verify. There is a difference between identifying specific children, and running programs that target children more generally; and / or having research that shows how your product harms children, and failing to do anything to stop it. We can tackle both of those issues without requiring age verification. We're headed down the path of age verification because we know now that not only is social media harmful, it's especially harmful to kids, and has been specifically targeted to them. Those are things that can be fixed, regardless of how you feel about age verification. Large corporate legal departments, wink-wink-nudge-nudge command and control hierarchies where nothing incriminating is ever put into writing, voluminous intra-office communications that bury even the circumstantial evidence so deeply no jury could understand it even if the plaintiffs/state could uncover it, etc.Anyone over the age of 12 that thinks corporate entities can be made to be accountable in a meaningful way is more than naive. Or is it that you realize they can't be held accountable but you'd rather maintain the status quo than contemplate a country which abolished them and enforced that all business was the conducted by sole proprietorships and (small-n) partnerships? Anyone over the age of 12 that thinks corporate entities can be made to be accountable in a meaningful way is more than naive. Or is it that you realize they can't be held accountable but you'd rather maintain the status quo than contemplate a country which abolished them and enforced that all business was the conducted by sole proprietorships and (small-n) partnerships? Give our personal devices have the ability to verify our age and identity securely and store on device like they do our fingerprint or face data.Services that need access only verify it cryptographically. So my iPhone can confirm I'm over 21 for my DoorDash app in the same way it stores my biometric data.The challenge here is the adoption of these encryption services and whether companies can rely on devices for that for compliance without having to cut off service for those without it set up. Services that need access only verify it cryptographically. So my iPhone can confirm I'm over 21 for my DoorDash app in the same way it stores my biometric data.The challenge here is the adoption of these encryption services and whether companies can rely on devices for that for compliance without having to cut off service for those without it set up. The challenge here is the adoption of these encryption services and whether companies can rely on devices for that for compliance without having to cut off service for those without it set up. It would allow someone with an mDL on their device to present only their age instead of other identifying information. I'd rather be saying "use whatbwe built, ita is better." There is no need for children to access the Internet full stop.Internet is a network in which everything can connect to everything, and every connected machine can run clients, servers, p2p nodes and what not. Controlling every possible endpoint your child might connect to is not feasible. Shutting the entire network down because "won't somebody please think of the children" is not acceptable.And, don't let them trick you. Internet is a network in which everything can connect to everything, and every connected machine can run clients, servers, p2p nodes and what not. Controlling every possible endpoint your child might connect to is not feasible. Shutting the entire network down because "won't somebody please think of the children" is not acceptable.And, don't let them trick you. and there is nothing I or the few (in terms of power) well-meaning government and corporate actors can do to change that. It doesn't have to be perfect and there will of course be easy workarounds to hid the warnings for people that want. Like putting information about the dangers of smoking on packages of smokes; it doesn't stop people from smoking but it does make the danger very easy to learn. Better than muddying the waters trying to make it less addictive but then letting them on there when their brains aren't ready. Similar to how there is specific channels for children on the TV. Perhaps the government can even incentivize such channels. Parents would only need to monitor if the tv is still tuned to disney channel or similar instead of some adult channels.Similarly this kind of method could be applied to online spaces. Similarly this kind of method could be applied to online spaces. Even the typical classroom count is far too large. This rebuttal to privacy preserving approaches isn't compelling. Websites can split the difference and use privacy preserving techniques when available, and fall back to other methods when the user doesn't have an ID. I'd go further and say websites should be required to prioritize privacy preserving techniques where available.There is a separate issue of improving access to government ID. I think that is important for reasons outside of age verification. Increasingly voting, banking, etc... already relies on having an ID. There is a separate issue of improving access to government ID. I think that is important for reasons outside of age verification. Increasingly voting, banking, etc... already relies on having an ID. In china there are places to scan you device and get coupons. usually at elevators in residential buildings so they can track also if you're arriving or leaving easily.In the US every store tracks and report to ad networks your Bluetooth ids. and we know what happens to ad networks.US now requires cars to report data, which was optional before (e.g. onstar) and china joined on this since the ev boom.the public id space is booming. In the US every store tracks and report to ad networks your Bluetooth ids. and we know what happens to ad networks.US now requires cars to report data, which was optional before (e.g. onstar) and china joined on this since the ev boom.the public id space is booming. US now requires cars to report data, which was optional before (e.g. onstar) and china joined on this since the ev boom.the public id space is booming. Most modern cars have one, but nothing prevents you from disabling or removing it. I certainly would not tolerate such a "bug" in by car.> In the US every store tracks and report to ad networks your Bluetooth ids.This also isn't true, modern phones randomize Bluetooth identifiers. > In the US every store tracks and report to ad networks your Bluetooth ids.This also isn't true, modern phones randomize Bluetooth identifiers. This also isn't true, modern phones randomize Bluetooth identifiers. So there is absolutely no way to change that and give out IDs from the age of 14? You can already get an ID for children in Germany https://www.germany.info/us-de/service/reisepass-und-persona...This is a problem that has to be solved by the government and not by private tech companies.This is a lazy cop out to say "we have tried nothing and we are all out of ideas" This is a problem that has to be solved by the government and not by private tech companies.This is a lazy cop out to say "we have tried nothing and we are all out of ideas" This is a lazy cop out to say "we have tried nothing and we are all out of ideas" Another example where this plays a role are voter registration and ID requirements for voting in the US. (This is a genuine question) please could you describe the underlying problem that age verification is attempting to solve? This is done in the physical world - why should digital be lawless when it applies to the same human behaviors?I've been addicted to a lot of digital media parts in harmful ways and I had the luck and support to grow out of most of it. A lot of people are not that lucky. A lot of people are not that lucky. The latter may not be great, but eating potato chips all day also probably isn't, and I don't think the government should outlaw minors eating potato chips. Gambling is always bad in the limit.A simple rule could probably be that if a website can make you lose over $200 of real money, it should probably require age verification. I don't see why other things should. A simple rule could probably be that if a website can make you lose over $200 of real money, it should probably require age verification. I don't see why other things should. The cynic in me says that's not why governments want identity confirmation for gambling websites. It's so you can't dodge the taxman You could buy 19 gallons of milk for that money (80 liters). There are options that don't involve any ID uploads whatsoever. For example, with a German ID you can provide proof that you are older than 18 without giving up any identifying information. If that happened in the US, Republicans would then:1. Insist that non-white children carry ID at all times2. Insist that non-white children carry ID at all times2. Now the issue of which properties can "ask to verify your age" and "apple now knows what you're looking at" is still an unsolved problem, but maybe that solution can be delivered by something like a one time offline token etc.But again, this is a very hard problem to solve and I would personally like to not have companies verify age etc. But again, this is a very hard problem to solve and I would personally like to not have companies verify age etc. Many of the worst present on the internet is not age gated at all, you have millions of porn websites without even a "are you over 18" popup. There are plethora of toxic forums...Of course it's a complex problem, but the current approach sacrifice a lot of what made the internet possible and I don't like it. Of course it's a complex problem, but the current approach sacrifice a lot of what made the internet possible and I don't like it. Aside from the privacy concerns, all this age verification tech seems incredibly complicated and expensive. Oh, remember those good old times when alcohol was kids' stuff....... For age verification specifically, the only information that services need proof of is that the users age is above a certain threshold. But in order to make this determination, we see services asking for government ID (which many 14-year-olds do not have), or for invasive face scans. that the identity is not being reused across many accountsAll the technologies exist for this, we just haven't put them together usefully. Zero knowledge proofs, like Groth16 or STARKs allow for statements about data to be validated externally without revealing the data itself. These are difficult for engineers to use, let alone consumers. Big opportunity for someone to build an authority here. that the identity is not being reused across many accountsAll the technologies exist for this, we just haven't put them together usefully. Zero knowledge proofs, like Groth16 or STARKs allow for statements about data to be validated externally without revealing the data itself. These are difficult for engineers to use, let alone consumers. Big opportunity for someone to build an authority here. that the identity is not being reused across many accountsAll the technologies exist for this, we just haven't put them together usefully. Zero knowledge proofs, like Groth16 or STARKs allow for statements about data to be validated externally without revealing the data itself. These are difficult for engineers to use, let alone consumers. Big opportunity for someone to build an authority here. that the identity is not being reused across many accountsAll the technologies exist for this, we just haven't put them together usefully. Zero knowledge proofs, like Groth16 or STARKs allow for statements about data to be validated externally without revealing the data itself. These are difficult for engineers to use, let alone consumers. Big opportunity for someone to build an authority here. 3. that the identity is not being reused across many accountsAll the technologies exist for this, we just haven't put them together usefully. Zero knowledge proofs, like Groth16 or STARKs allow for statements about data to be validated externally without revealing the data itself. These are difficult for engineers to use, let alone consumers. Big opportunity for someone to build an authority here. All the technologies exist for this, we just haven't put them together usefully. Zero knowledge proofs, like Groth16 or STARKs allow for statements about data to be validated externally without revealing the data itself. These are difficult for engineers to use, let alone consumers. Big opportunity for someone to build an authority here. like most proposed solutions, this just seems overcomplicated. we don't need "accessible cryptographic infrastructure for human identity". just piggy-back on that infrastructure.1) government makes a database of valid "over 18" unique identifiers (UUIDs)2) government provides tokens with a unique identifier on it to various stores that already sell age-restricted products (e.g. gas stations, liquor stores)3) people buy a token from the store, only having to show their ID to the store clerk that they already show their ID to for smokes (no peter thiel required)4) website accepts the token and queries the government database and sees "yep, over 18"easy. no need for fancy zero-knowledge proofs or on-device whatevers. 1) government makes a database of valid "over 18" unique identifiers (UUIDs)2) government provides tokens with a unique identifier on it to various stores that already sell age-restricted products (e.g. gas stations, liquor stores)3) people buy a token from the store, only having to show their ID to the store clerk that they already show their ID to for smokes (no peter thiel required)4) website accepts the token and queries the government database and sees "yep, over 18"easy. no need for fancy zero-knowledge proofs or on-device whatevers. 2) government provides tokens with a unique identifier on it to various stores that already sell age-restricted products (e.g. gas stations, liquor stores)3) people buy a token from the store, only having to show their ID to the store clerk that they already show their ID to for smokes (no peter thiel required)4) website accepts the token and queries the government database and sees "yep, over 18"easy. no need for fancy zero-knowledge proofs or on-device whatevers. 3) people buy a token from the store, only having to show their ID to the store clerk that they already show their ID to for smokes (no peter thiel required)4) website accepts the token and queries the government database and sees "yep, over 18"easy. no need for fancy zero-knowledge proofs or on-device whatevers. no need for fancy zero-knowledge proofs or on-device whatevers. no need for fancy zero-knowledge proofs or on-device whatevers. to go on tiktok, you enter a UUID once onto your account, and thats it. all of the enforcement laws already exist.>Why should I have to share more than required?you shouldnt. all of the enforcement laws already exist.>Why should I have to share more than required?you shouldnt. >Why should I have to share more than required?you shouldnt. Having said that, I think having an "I'm of legal age" tickbox goes quite far enough.For the ultra-controlling, setting up a "kid's account" using the tools already provided in mainstream OS's [0][1] is a fine option. For the ultra-controlling, setting up a "kid's account" using the tools already provided in mainstream OS's [0][1] is a fine option. no, it is exactly as protective as the protections for purchasing alcohol or buying smokes or other controlled substances/products.buying smokes/alcohol when underage is obviously harder than "click this box". (did you ever try to buy smokes/alcohol when underage? you cant just go up to the clerk at the store when you are 14 and say "trust me bro, im 18/19/21". )>Anyone who is of legal age can buy UUIDs and pass them around to folks who are not.same for smoking and alcohol. we can apply those laws to your internet-age-token.most people seem fine with the current trade-off for smokes/alcohol. i see no reason why tiktok needs to be treated as more dangerous than either.>Having said that, I think having an "I'm of legal age" tickbox goes quite far enough.i agree with this and everything you said afterwards. buying smokes/alcohol when underage is obviously harder than "click this box". (did you ever try to buy smokes/alcohol when underage? you cant just go up to the clerk at the store when you are 14 and say "trust me bro, im 18/19/21". )>Anyone who is of legal age can buy UUIDs and pass them around to folks who are not.same for smoking and alcohol. we can apply those laws to your internet-age-token.most people seem fine with the current trade-off for smokes/alcohol. i see no reason why tiktok needs to be treated as more dangerous than either.>Having said that, I think having an "I'm of legal age" tickbox goes quite far enough.i agree with this and everything you said afterwards. >Anyone who is of legal age can buy UUIDs and pass them around to folks who are not.same for smoking and alcohol. we can apply those laws to your internet-age-token.most people seem fine with the current trade-off for smokes/alcohol. i see no reason why tiktok needs to be treated as more dangerous than either.>Having said that, I think having an "I'm of legal age" tickbox goes quite far enough.i agree with this and everything you said afterwards. we can apply those laws to your internet-age-token.most people seem fine with the current trade-off for smokes/alcohol. i see no reason why tiktok needs to be treated as more dangerous than either.>Having said that, I think having an "I'm of legal age" tickbox goes quite far enough.i agree with this and everything you said afterwards. we can apply those laws to your internet-age-token.most people seem fine with the current trade-off for smokes/alcohol. i see no reason why tiktok needs to be treated as more dangerous than either.>Having said that, I think having an "I'm of legal age" tickbox goes quite far enough.i agree with this and everything you said afterwards. most people seem fine with the current trade-off for smokes/alcohol. i see no reason why tiktok needs to be treated as more dangerous than either.>Having said that, I think having an "I'm of legal age" tickbox goes quite far enough.i agree with this and everything you said afterwards. >Having said that, I think having an "I'm of legal age" tickbox goes quite far enough.i agree with this and everything you said afterwards. i agree with this and everything you said afterwards. Unlike with the proposed ID-collection-and-retention schemes (that are authoritarian's wet dreams) the vendor of the UUID is not responsible for ensuring that that UUID is not later used by someone who is not of-age.If you were to -say- make alcohol vendors liable for the actions of of-age people who pass on alcohol to not-of-age people, then you'd see serious attempts to control distribution. [0] Don't forget the existence of preexisting parental controls in every major OS. IME, this is a hurdle that's at least as difficult to surmount as the ID check done in non-chain convenience stores. [0] Don't forget the existence of preexisting parental controls in every major OS. IME, this is a hurdle that's at least as difficult to surmount as the ID check done in non-chain convenience stores. [0] Don't forget the existence of preexisting parental controls in every major OS. IME, this is a hurdle that's at least as difficult to surmount as the ID check done in non-chain convenience stores. they will be declined.>As I mentioned, any of-age person can distribute those UUIDs to people who are not of-age.again... same with smokes and alcohol! but we are okay with how smokes and alcohol are regulated right now.tiktok is not worse than a bottle of vodka. we are okay with how vodka is regulated. tiktok does not need even more strict age-verification than vodka.it is not perfect, but it is absolutely more stringent than a checkbox. they will be declined.>As I mentioned, any of-age person can distribute those UUIDs to people who are not of-age.again... same with smokes and alcohol! but we are okay with how smokes and alcohol are regulated right now.tiktok is not worse than a bottle of vodka. we are okay with how vodka is regulated. tiktok does not need even more strict age-verification than vodka.it is not perfect, but it is absolutely more stringent than a checkbox. they will be declined.>As I mentioned, any of-age person can distribute those UUIDs to people who are not of-age.again... same with smokes and alcohol! but we are okay with how smokes and alcohol are regulated right now.tiktok is not worse than a bottle of vodka. we are okay with how vodka is regulated. tiktok does not need even more strict age-verification than vodka.it is not perfect, but it is absolutely more stringent than a checkbox. >As I mentioned, any of-age person can distribute those UUIDs to people who are not of-age.again... same with smokes and alcohol! but we are okay with how smokes and alcohol are regulated right now.tiktok is not worse than a bottle of vodka. we are okay with how vodka is regulated. tiktok does not need even more strict age-verification than vodka.it is not perfect, but it is absolutely more stringent than a checkbox. but we are okay with how smokes and alcohol are regulated right now.tiktok is not worse than a bottle of vodka. we are okay with how vodka is regulated. tiktok does not need even more strict age-verification than vodka.it is not perfect, but it is absolutely more stringent than a checkbox. tiktok is not worse than a bottle of vodka. we are okay with how vodka is regulated. tiktok does not need even more strict age-verification than vodka.it is not perfect, but it is absolutely more stringent than a checkbox. (Also, like, did you ever go to college? Live in a dorm or apartment with underage students? Everyone knew it was happening all the damn time. )> they are obviously not liable if i buy something legitimately, go home, and feed it to my kid. in that case, i am liable...And if you changed up the rules to make them liable, you'd see serious attempts at controlling distribution.What has been the state of the art in parental controls for quite some time is like the current regulatory regime for booze and tobacco. [0]What's being proposed and is currently implemented by several big-name sites is even more invasive.> we are okay with how smokes and alcohol works right now.I'm not. Either booze and tobacco need to be made into Schedule I substances, or their regulation needs to become much more lax. But I recognize that my opinion on the topic is considered to be somewhat out-of-the-ordinary. > they are obviously not liable if i buy something legitimately, go home, and feed it to my kid. in that case, i am liable...And if you changed up the rules to make them liable, you'd see serious attempts at controlling distribution.What has been the state of the art in parental controls for quite some time is like the current regulatory regime for booze and tobacco. [0]What's being proposed and is currently implemented by several big-name sites is even more invasive.> we are okay with how smokes and alcohol works right now.I'm not. Either booze and tobacco need to be made into Schedule I substances, or their regulation needs to become much more lax. But I recognize that my opinion on the topic is considered to be somewhat out-of-the-ordinary. [0]What's being proposed and is currently implemented by several big-name sites is even more invasive.> we are okay with how smokes and alcohol works right now.I'm not. Either booze and tobacco need to be made into Schedule I substances, or their regulation needs to become much more lax. But I recognize that my opinion on the topic is considered to be somewhat out-of-the-ordinary. [0]What's being proposed and is currently implemented by several big-name sites is even more invasive.> we are okay with how smokes and alcohol works right now.I'm not. Either booze and tobacco need to be made into Schedule I substances, or their regulation needs to become much more lax. But I recognize that my opinion on the topic is considered to be somewhat out-of-the-ordinary. What's being proposed and is currently implemented by several big-name sites is even more invasive.> we are okay with how smokes and alcohol works right now.I'm not. Either booze and tobacco need to be made into Schedule I substances, or their regulation needs to become much more lax. But I recognize that my opinion on the topic is considered to be somewhat out-of-the-ordinary. > we are okay with how smokes and alcohol works right now.I'm not. Either booze and tobacco need to be made into Schedule I substances, or their regulation needs to become much more lax. But I recognize that my opinion on the topic is considered to be somewhat out-of-the-ordinary. Either booze and tobacco need to be made into Schedule I substances, or their regulation needs to become much more lax. But I recognize that my opinion on the topic is considered to be somewhat out-of-the-ordinary. so we are stuck trying to figure something else out. do i wish we could just use the existing basic parental controls instead of whatever the hell we are going to end up with? obviously!the easiest "something else" is to piggy-back on existing age-restriction regulations (i.e. smokes, alcohol, gambling) because they have broad (obviously not ubiquitous, but broad) support. the easiest "something else" is to piggy-back on existing age-restriction regulations (i.e. smokes, alcohol, gambling) because they have broad (obviously not ubiquitous, but broad) support. Consider that such arguments (just like the arguments of Prohibitionists that resulted in the rise to power of Organized Crime) are made in a varied combination of ignorance and bad faith, and that we should loudly reject them in the strongest possible terms.To be clear, I'm asserting that the claim that preexisting parental controls are insufficient is an argument made in ignorance and bad faith, not your assertion that the argument is being made. To be clear, I'm asserting that the claim that preexisting parental controls are insufficient is an argument made in ignorance and bad faith, not your assertion that the argument is being made. me and you can yell into the void all we want. and i will continue to do so!but, age verification is already here. so while i continue to yell about how stupid it is, i am also going to propose options that i feel like are less bad than what is being actively rolled out right now. so while i continue to yell about how stupid it is, i am also going to propose options that i feel like are less bad than what is being actively rolled out right now. What we have now has been roundly rejected by the authoritarians pushing this expansion of power and influence. Your time and energy are better spent resisting the expansion, rather than suggesting alternatives that those authoritarians will never accept. No matter what the actual mechanism is, I guarantee they will insist on something like that. if the goal is "surveil everyone using the internet", yes, very obviously my proposal would not be selected, and you will have to upload your id to various 3rd-party id verifiers. I'm not sure that's the right answer here, but I think it ticks a lot boxes for the state. As it is we're seeing companies capture IDs and face scans and it's incredibly invasive relative to the need - "prove your birth year is in range". My state already has a gov't ID that can be added to an apple wallet. Extending that to support proofs about identity without requiring users to unmask huge amounts of personal information would be valuable in its own right. At this point I think the challenge has less to do with the crypto primitives and more to do with building infrastructure that hides 100% of the complexity of identity validation from users. My state already has a gov't ID that can be added to an apple wallet. Extending that to support proofs about identity without requiring users to unmask huge amounts of personal information would be valuable in its own right. Your crypto nerd dream is vulnerable to the fact that someone under 18 can just ask someone over 18 to make an account for them. All age verification is broken in this way.There is a similar problem for people using apps like Ubereats to work illegally by buying an account from someone else. There is a similar problem for people using apps like Ubereats to work illegally by buying an account from someone else. Generally they don't, because that's the cops' job. Teenagers can easily get their hands on alcohol... you just need to know the right person at school who has a cool older brother. If their older brother is really cool they can get weed too!The police absolutely do not have the time to investigate the crime of making a discord account for someone. They don't care whether you are 14 or not. "Think of the children" is just a pretense. Governments (and a few companies) really want this. The site guidelines ask users to send those to us at hn@ycombinator.com rather than post about it in the threads, but we always look into such cases when people send them.It almost invariably turns out to simply be that the community is divided on a topic, and this is usually demonstrable even from the public data (such as comment histories). It almost invariably turns out to simply be that the community is divided on a topic, and this is usually demonstrable even from the public data (such as comment histories). The cynic in me fears they don't want a privacy-preserving solution, which blinds them to 'who'. Because that would satisfy parents worried about their kids and many privacy conscious folks.Rather, they want a blank check to blackmail or imprison only their opponents. Rather, they want a blank check to blackmail or imprison only their opponents. "Citizens will be on their best behavior, because we're constantly recording and reporting everything that is going on" - Larry Ellison(I seem to recall from the context of the quote, he isn't saying this is the future he wants, but it's a future he's not particularly opposed to)But the real threat is "accidental" database leaks from private websites. Let's say you live in a state where abortion isn't legal, and you sign up for a web forum where people discuss getting out-of-state abortions. As soon as that website is required to collect real names (which it will be), it becomes unusable, because nobody can risk getting doxxed. (I seem to recall from the context of the quote, he isn't saying this is the future he wants, but it's a future he's not particularly opposed to)But the real threat is "accidental" database leaks from private websites. Let's say you live in a state where abortion isn't legal, and you sign up for a web forum where people discuss getting out-of-state abortions. As soon as that website is required to collect real names (which it will be), it becomes unusable, because nobody can risk getting doxxed. But the real threat is "accidental" database leaks from private websites. Let's say you live in a state where abortion isn't legal, and you sign up for a web forum where people discuss getting out-of-state abortions. As soon as that website is required to collect real names (which it will be), it becomes unusable, because nobody can risk getting doxxed. When I challenged him on his rhetoric, my comment INSTANTLY disappeared. I thought maybe it was a fluke, so I tried again, and the next comment insta-disappeared also.Soon thereafter I was locked out of the account and asked to provide a "selfie" to confirm my identity. Soon thereafter I was locked out of the account and asked to provide a "selfie" to confirm my identity. This is true of basically any issue discussed on the internet. How do you know what is "shared talking points" vs "humans learning arguments from others" and simply echoing those? Unless you work at one of the social media platforms, isn't it short of impossible to know what exactly you're looking at? Filtering age-appropriate contentI'm sure there are many other points with various degree of validity. Filtering age-appropriate contentI'm sure there are many other points with various degree of validity. Filtering age-appropriate contentI'm sure there are many other points with various degree of validity. Filtering age-appropriate contentI'm sure there are many other points with various degree of validity. I'm sure there are many other points with various degree of validity. Instead it would be more appropriate to let sites pass headers, such as "we have adult content", thst you could filter on the network or client side. Anyone will just visit sites that don't have the checks if necessary. One of the huge reasons for the First Amendment is to ensure that people are able to counter lies uttered in the public sphere with truth.#3 is handled by parental controls that have existed in mainstream OSs for quite some time now. [0][1][2] However, those preexisting parental controls don't justify additional expansion of the power and influence of authoritarians, so here we are. #3 is handled by parental controls that have existed in mainstream OSs for quite some time now. [0][1][2] However, those preexisting parental controls don't justify additional expansion of the power and influence of authoritarians, so here we are. If we're in the middle of an ongoing political debate, it doesn't seem that far fetched for me that people reach similar conclusions. What you're hearing then isn't "astro-turfing" but one coalition, of potentially many.I often hear people terrified that the government will have a say on what they view online, while being just fine with google doing the same. You can agree or disagree with my assesment, but the point is that hearing that point a bunch doesn't mean it's google astroturfing. It means all those people have a similar opinion, probably from reading the same blogs. I often hear people terrified that the government will have a say on what they view online, while being just fine with google doing the same. You can agree or disagree with my assesment, but the point is that hearing that point a bunch doesn't mean it's google astroturfing. It means all those people have a similar opinion, probably from reading the same blogs. But I don't think we need 99.99% confidence -- isn't even acknowledged that 30% of twitter is bots or something? I think it's safe to conclude there's astroturfing on any significant political issue.Also as far as documented cases, there were documented cases of astroturfing around fracking [1], or pesticides [2]1. https://journals.sagepub.com/doi/10.1177/2057047320969435 2. https://www.corywatson.com/blog/monsanto-downplay-roundup-ri... Also as far as documented cases, there were documented cases of astroturfing around fracking [1], or pesticides [2]1. https://journals.sagepub.com/doi/10.1177/2057047320969435 2. https://www.corywatson.com/blog/monsanto-downplay-roundup-ri... How do you suppose it is that millions of people, separated by vast geographic distances, somehow all reach similar conclusions all at once?Related: How do you suppose it is that out of 350-700+ million people (depending on whose numbers you believe), there's always only two "choices" and both of them suck? Related: How do you suppose it is that out of 350-700+ million people (depending on whose numbers you believe), there's always only two "choices" and both of them suck? In the same way that patriarchy rose amongst them all.In the same way that a shared currency was deemed necessary.Escpecially in matters of governance, there is something to be said about how humans like to organise themselves. No country has truly escaped capitalism so far. In the same way that a shared currency was deemed necessary.Escpecially in matters of governance, there is something to be said about how humans like to organise themselves. No country has truly escaped capitalism so far. No country has truly escaped capitalism so far. "Real" user verification is a wet dream to googlr, meta, etc. Its both a ad inflation and a competive roadblock.The benefits are real: teens are being preyed upon and socially maligned. Unsurprising because no one trusts gov, but then implicitly trust business?Yeah, so obviously, its implementation that will just move around harms. Unsurprising because no one trusts gov, but then implicitly trust business?Yeah, so obviously, its implementation that will just move around harms. The technology is not there nor are governments coordinating appropiate digital concerns. Unsurprising because no one trusts gov, but then implicitly trust business?Yeah, so obviously, its implementation that will just move around harms. Yeah, so obviously, its implementation that will just move around harms. Groups of people who wake up at the same time of the day often have a tendency to be from a similar place, hold similar values and consume similar media.Just because a bunch of people came to the same conclusion and have had their opinions coalesce around some common ideas, doesn't mean it's astroturfing. Just because a bunch of people came to the same conclusion and have had their opinions coalesce around some common ideas, doesn't mean it's astroturfing. Things that didn't seem likely to have broad support previously, now are seen as acceptable. In the 90's no one could envision rounding up immigrants. No one could envision uploading an ID card to use ICQ. And they seem to have stocked the Supreme Court to make all these kinds of things a reality.All because the rest of us keep dismissing all of this as just harmless extreme positions that no one in society really supports. We have to start fighting things like this with more than, "It's not real." Today, in the US for instance, there are entire new generations of people alive. And they seem to have stocked the Supreme Court to make all these kinds of things a reality.All because the rest of us keep dismissing all of this as just harmless extreme positions that no one in society really supports. We have to start fighting things like this with more than, "It's not real." All because the rest of us keep dismissing all of this as just harmless extreme positions that no one in society really supports. We have to start fighting things like this with more than, "It's not real." Both Clinton and Obama deported way more people than Trump. And Clinton only deported 2 million across his entire 8 years in office. IE - "Returns" were people who showed up at the border, sea port, airport or border checkpoint; asked to get in, and we said no. He didn't, however, round up immigrants living in the US on this scale and deport them like we're seeing today. People would never have allowed for that.To put numbers on it, Trump is on year 5, and has already processed more formal removal orders than Clinton did by year 8. Not only that, voluntary removals were near non-existent under Clinton in the 90's. Today, for just this year alone, they sit at around 1.5 million. IE - "Returns" were people who showed up at the border, sea port, airport or border checkpoint; asked to get in, and we said no. He didn't, however, round up immigrants living in the US on this scale and deport them like we're seeing today. People would never have allowed for that.To put numbers on it, Trump is on year 5, and has already processed more formal removal orders than Clinton did by year 8. Not only that, voluntary removals were near non-existent under Clinton in the 90's. Today, for just this year alone, they sit at around 1.5 million. What you mean is that Clinton simply didn't let anyone into the country. He didn't, however, round up immigrants living in the US on this scale and deport them like we're seeing today. People would never have allowed for that.To put numbers on it, Trump is on year 5, and has already processed more formal removal orders than Clinton did by year 8. Not only that, voluntary removals were near non-existent under Clinton in the 90's. Today, for just this year alone, they sit at around 1.5 million. To put numbers on it, Trump is on year 5, and has already processed more formal removal orders than Clinton did by year 8. Not only that, voluntary removals were near non-existent under Clinton in the 90's. Today, for just this year alone, they sit at around 1.5 million. Further, I suggest that Democrats and Democrat-controlled media cultivate a delusional worldview which allows their supporters to ignore the right-wing brutality consistently and continually imposed by Democrat leaders.How do you feel about the second Trump admin's nationwide, made-for-TV DHS/ICE siege? How do you feel about the second Trump admin's nationwide, made-for-TV DHS/ICE siege? Never take TV seriously.The key mistake is even watching it in the first place. - Governments benefit from easier monitoring and enforcement.- The advertising industry prefers verified identities for better targeting.- Social media companies gain more reliable data and engagement.- Online shopping companies can reduce fraud and increase tracking.- Many SaaS companies would also welcome stronger identity verification.In short, anonymity is not very profitable, and governments often favor identification because it increases oversight and control.Of course, this leads to political debate. However, one could argue that access to the internet has become a fundamental part of modern life as well. It may not be explicitly written into the Constitution, but in practice it functions as an essential right in today's society. - The advertising industry prefers verified identities for better targeting.- Social media companies gain more reliable data and engagement.- Online shopping companies can reduce fraud and increase tracking.- Many SaaS companies would also welcome stronger identity verification.In short, anonymity is not very profitable, and governments often favor identification because it increases oversight and control.Of course, this leads to political debate. However, one could argue that access to the internet has become a fundamental part of modern life as well. It may not be explicitly written into the Constitution, but in practice it functions as an essential right in today's society. - Social media companies gain more reliable data and engagement.- Online shopping companies can reduce fraud and increase tracking.- Many SaaS companies would also welcome stronger identity verification.In short, anonymity is not very profitable, and governments often favor identification because it increases oversight and control.Of course, this leads to political debate. However, one could argue that access to the internet has become a fundamental part of modern life as well. It may not be explicitly written into the Constitution, but in practice it functions as an essential right in today's society. - Online shopping companies can reduce fraud and increase tracking.- Many SaaS companies would also welcome stronger identity verification.In short, anonymity is not very profitable, and governments often favor identification because it increases oversight and control.Of course, this leads to political debate. However, one could argue that access to the internet has become a fundamental part of modern life as well. It may not be explicitly written into the Constitution, but in practice it functions as an essential right in today's society. - Many SaaS companies would also welcome stronger identity verification.In short, anonymity is not very profitable, and governments often favor identification because it increases oversight and control.Of course, this leads to political debate. However, one could argue that access to the internet has become a fundamental part of modern life as well. It may not be explicitly written into the Constitution, but in practice it functions as an essential right in today's society. In short, anonymity is not very profitable, and governments often favor identification because it increases oversight and control.Of course, this leads to political debate. However, one could argue that access to the internet has become a fundamental part of modern life as well. It may not be explicitly written into the Constitution, but in practice it functions as an essential right in today's society. However, one could argue that access to the internet has become a fundamental part of modern life as well. It may not be explicitly written into the Constitution, but in practice it functions as an essential right in today's society. Realizing that much of the internet is totally toxic to children now and should have a means of keeping them out is distinct from agreeing to upload ID to everything.A better implementation would be to have a device/login level parental control setting that passed age restriction signals via browsers and App Stores. This is both a simpler design and privacy friendly. A better implementation would be to have a device/login level parental control setting that passed age restriction signals via browsers and App Stores. This is both a simpler design and privacy friendly. At least here in US: Google/Apple device controls allow app to request whether user meets age requirements. If so, let through, if not, can't proceed through door.I know I am oversimplifying.But I like this approach vs. uploading an ID to TikTok. But I like this approach vs. uploading an ID to TikTok. parents need to start parenting by taking responsibility on what their kids are doing, and government should start governing with regulations on ad tech, addictive social media platforms, instead of using easily hackable platforms for de anonymization, which in turn enable mass identity theft. They actually want DEVICE based ID.I want LESS things that are tied to me financially and legally to be stolen when(not if) these services and my device are compromised. They actually want DEVICE based ID.I want LESS things that are tied to me financially and legally to be stolen when(not if) these services and my device are compromised. I want LESS things that are tied to me financially and legally to be stolen when(not if) these services and my device are compromised. I also think the FUD they've succeeded in creating around the use of LLMs for code generation (there's a portion of the management class that seems to genuinely believe that Claude Code is AGI) is the greatest marketing operation of our lifetimes. Automatic shaping of online community discussions (social media, bots, etc)2. Automatic datamining, manipulating and reacting to all digitally communicated conversations (think dropping calls or MITM manipulation of conversations between organizers of a rival poltical party in swing districts proir to an election, etc. Automatic datamining, manipulating and reacting to all digitally communicated conversations (think dropping calls or MITM manipulation of conversations between organizers of a rival poltical party in swing districts proir to an election, etc. That being said, this is a 1 bit information, adult in current legislation yes/no. I consider it a huge success of the Internet architects that we were able to create a protocol and online culture resilient for over 3 decades to this legacy meatspace nonsense.> That being said, this is a 1 bit information, adult in current legislation yes/no.If that's all it would take to satisfy legislatures forever, and the implementation was left up to the browser (`return 1`) I'd be all for it. Unfortunately the political interests here want way more than that. > That being said, this is a 1 bit information, adult in current legislation yes/no.If that's all it would take to satisfy legislatures forever, and the implementation was left up to the browser (`return 1`) I'd be all for it. Unfortunately the political interests here want way more than that. If that's all it would take to satisfy legislatures forever, and the implementation was left up to the browser (`return 1`) I'd be all for it. Unfortunately the political interests here want way more than that. From what I've seen, most of the pro-ID commenters are coming from positions where they assume ID checks will only apply to other people, not them. So we should probably get ahead of this debate and push for good ways to do part-of-identity-checks. Because I don't see any good way to avoid them.We could potentially do ID checks that only show exactly what the receiver needs to know and nothing else. We could potentially do ID checks that only show exactly what the receiver needs to know and nothing else. A stronger statement: we know how to build zero-knowledge proofs over government-issued identification, cf. https://zkpassport.id/The services that use these proofs then need to implement that only one device can be logged in with a given identity at a time, plus some basic rate limiting on logins, and the problem is solved. The services that use these proofs then need to implement that only one device can be logged in with a given identity at a time, plus some basic rate limiting on logins, and the problem is solved. I think a lot of the younger generation supports it, actually. Do you think strip clubs and bars should stop IDing people at the door? This would be impractical in meatspace, but works perfectly fine on the internet. [edit] I did a little reading and it sounds like the company does not query the government with your ID. You get the cryptographic ID from the government, and present it to a company who is able to verify its validity directly. Actually, yes, it seems to have shifted quite a bit. As far as I can tell, it seems correlated with the amount of mis/disinformation on the web, and acceptance of more fringe views, that seems to make one group more vocal about wanting to ensure only "real people" share what they think on the internet, and a sub-section of that group wanting to enforce this "real name" policy too.It in itself used to be fringe, but really been catching on in mainstream circles, where people tend to ask themselves "But I don't have anything to hide, and I already use my real name, why cannot everyone do so too?" It in itself used to be fringe, but really been catching on in mainstream circles, where people tend to ask themselves "But I don't have anything to hide, and I already use my real name, why cannot everyone do so too?" No matter how well the tech literate person secures their privacy it has become clear that some Corpo will eventually release everything in an "accident" that causes their efforts to become meaningless.After a while it's only human for fatigue to build up. You can't stop your information from getting out there. Taking steps to secure your information ironically just makes you stand out more and narrows the pool you're in to make it easier to find you and your information. And again you're always just one "bug" from having it all be for nothing.I still take some steps to secure my privacy, I'm not out there shouting my social security information or real name. After a while it's only human for fatigue to build up. You can't stop your information from getting out there. Taking steps to secure your information ironically just makes you stand out more and narrows the pool you're in to make it easier to find you and your information. And again you're always just one "bug" from having it all be for nothing.I still take some steps to secure my privacy, I'm not out there shouting my social security information or real name. Meanwhile every Corpo out there in tech is deliberately creating ways to track you and extract your personal information. Taking steps to secure your information ironically just makes you stand out more and narrows the pool you're in to make it easier to find you and your information. And again you're always just one "bug" from having it all be for nothing.I still take some steps to secure my privacy, I'm not out there shouting my social security information or real name. I still take some steps to secure my privacy, I'm not out there shouting my social security information or real name. It's always, 100% of the time, inevitably, without exception, a tool used by petty bureaucrats and power hungry politicians to exert power and control over the citizens they are supposed to represent.They might use it on a couple of token examples for propaganda purposes, but if you look throughout the world where laws like this are implemented, authoritarian countries and western "democracies" alike, these laws are used to control locals. It's almost refreshingly straightforward and honest when a country just does the authoritarian things, instead of doing all the weaselly mental gymnastics to justify their power grabs.People who support this are ignorant or ideologically aligned with authoritarianism. They might use it on a couple of token examples for propaganda purposes, but if you look throughout the world where laws like this are implemented, authoritarian countries and western "democracies" alike, these laws are used to control locals. It's almost refreshingly straightforward and honest when a country just does the authoritarian things, instead of doing all the weaselly mental gymnastics to justify their power grabs.People who support this are ignorant or ideologically aligned with authoritarianism. People who support this are ignorant or ideologically aligned with authoritarianism. Then if the story gains traction and reaches the front page a more diverse and thoughtful group weighs in. Finally the story moves to EU or US and gets a whole new fresh take.I'm not surprised that people who support something are the ones most tuned in to the discussion because for anyone opposed they also have their own unrelated thing they care about. Then if the story gains traction and reaches the front page a more diverse and thoughtful group weighs in. Finally the story moves to EU or US and gets a whole new fresh take.I'm not surprised that people who support something are the ones most tuned in to the discussion because for anyone opposed they also have their own unrelated thing they care about. I'm not surprised that people who support something are the ones most tuned in to the discussion because for anyone opposed they also have their own unrelated thing they care about. HN has largely shifted away from tech literacy and towards business literacy in recent years.Needless to say that an internet where every user's real identity is easily verifiable at all times is very beneficial for most businesses, so it's natural to see that stance here. Needless to say that an internet where every user's real identity is easily verifiable at all times is very beneficial for most businesses, so it's natural to see that stance here. These are not the same people from 30 years ago. The new generation has come to love big brother. All it took to sell their soul was karma points. I dont think they want to figure it out. They think the internet should be stagnant unchanging and eternal as it currently exists because it makes the most money. The short version is that voters want government to bring tech to heel.From what I see, people are tired of tech, social media, and enshittified apps. AI hype, talk of the singularity, and fears about job loss have pushed things well past grim.Recent social media bans indicate how far voter tolerance for control and regulation has shifted.This is problematic because government is also looking for reasons to do so. Partly because big tech is simply dominant, and partly because governments are trending toward authoritarianism.The solution would have been research that helped create targeted and effective policy. Unfortunately, tech (especially social media) is naturally hostile to research that may paint its work as unhealthy or harmful.Tech firms are burned by exposés, user apathy, and a desire to keep getting paid.The lack of open research and access to data blocks the creation of knowledge and empirical evidence, which are the cornerstones of nuanced, narrowly tailored policy.The only things left on the table are blunt instruments, such as age verification. From what I see, people are tired of tech, social media, and enshittified apps. AI hype, talk of the singularity, and fears about job loss have pushed things well past grim.Recent social media bans indicate how far voter tolerance for control and regulation has shifted.This is problematic because government is also looking for reasons to do so. Partly because big tech is simply dominant, and partly because governments are trending toward authoritarianism.The solution would have been research that helped create targeted and effective policy. Unfortunately, tech (especially social media) is naturally hostile to research that may paint its work as unhealthy or harmful.Tech firms are burned by exposés, user apathy, and a desire to keep getting paid.The lack of open research and access to data blocks the creation of knowledge and empirical evidence, which are the cornerstones of nuanced, narrowly tailored policy.The only things left on the table are blunt instruments, such as age verification. Recent social media bans indicate how far voter tolerance for control and regulation has shifted.This is problematic because government is also looking for reasons to do so. Partly because big tech is simply dominant, and partly because governments are trending toward authoritarianism.The solution would have been research that helped create targeted and effective policy. Unfortunately, tech (especially social media) is naturally hostile to research that may paint its work as unhealthy or harmful.Tech firms are burned by exposés, user apathy, and a desire to keep getting paid.The lack of open research and access to data blocks the creation of knowledge and empirical evidence, which are the cornerstones of nuanced, narrowly tailored policy.The only things left on the table are blunt instruments, such as age verification. Partly because big tech is simply dominant, and partly because governments are trending toward authoritarianism.The solution would have been research that helped create targeted and effective policy. Unfortunately, tech (especially social media) is naturally hostile to research that may paint its work as unhealthy or harmful.Tech firms are burned by exposés, user apathy, and a desire to keep getting paid.The lack of open research and access to data blocks the creation of knowledge and empirical evidence, which are the cornerstones of nuanced, narrowly tailored policy.The only things left on the table are blunt instruments, such as age verification. The solution would have been research that helped create targeted and effective policy. Unfortunately, tech (especially social media) is naturally hostile to research that may paint its work as unhealthy or harmful.Tech firms are burned by exposés, user apathy, and a desire to keep getting paid.The lack of open research and access to data blocks the creation of knowledge and empirical evidence, which are the cornerstones of nuanced, narrowly tailored policy.The only things left on the table are blunt instruments, such as age verification. Tech firms are burned by exposés, user apathy, and a desire to keep getting paid.The lack of open research and access to data blocks the creation of knowledge and empirical evidence, which are the cornerstones of nuanced, narrowly tailored policy.The only things left on the table are blunt instruments, such as age verification. Yes.Or more honestly, there was always an undercurrent of paternalistic thought and tech regulation from the Columbine Massacre days [0] to today.Also for those of us who are younger (below 35) we grew up in an era where anonymized cyberbullying was normalized [1] and amongst whom support for regulating social media and the internet is stronger [2].The reality is, younger Americans on both sides of the aisle now support a more expansive government, but for their party.There is a second order impact of course, but most Americans (younger and older) don't realize that, and frankly, using the same kind of rhetoric from the Assange/Wikileaks, SOPA, and the GPG days just doesn't resonate and is out of touch.Gen X Techno-libertarianism isn't counterculture anymore, it's the status quo. And the modern "tech-literate" uses GitHub, LinkedIn, Venmo, Discord, TikTok, Netflix, and other services that are already attached to their identity. Or more honestly, there was always an undercurrent of paternalistic thought and tech regulation from the Columbine Massacre days [0] to today.Also for those of us who are younger (below 35) we grew up in an era where anonymized cyberbullying was normalized [1] and amongst whom support for regulating social media and the internet is stronger [2].The reality is, younger Americans on both sides of the aisle now support a more expansive government, but for their party.There is a second order impact of course, but most Americans (younger and older) don't realize that, and frankly, using the same kind of rhetoric from the Assange/Wikileaks, SOPA, and the GPG days just doesn't resonate and is out of touch.Gen X Techno-libertarianism isn't counterculture anymore, it's the status quo. And the modern "tech-literate" uses GitHub, LinkedIn, Venmo, Discord, TikTok, Netflix, and other services that are already attached to their identity. Also for those of us who are younger (below 35) we grew up in an era where anonymized cyberbullying was normalized [1] and amongst whom support for regulating social media and the internet is stronger [2].The reality is, younger Americans on both sides of the aisle now support a more expansive government, but for their party.There is a second order impact of course, but most Americans (younger and older) don't realize that, and frankly, using the same kind of rhetoric from the Assange/Wikileaks, SOPA, and the GPG days just doesn't resonate and is out of touch.Gen X Techno-libertarianism isn't counterculture anymore, it's the status quo. And the modern "tech-literate" uses GitHub, LinkedIn, Venmo, Discord, TikTok, Netflix, and other services that are already attached to their identity. The reality is, younger Americans on both sides of the aisle now support a more expansive government, but for their party.There is a second order impact of course, but most Americans (younger and older) don't realize that, and frankly, using the same kind of rhetoric from the Assange/Wikileaks, SOPA, and the GPG days just doesn't resonate and is out of touch.Gen X Techno-libertarianism isn't counterculture anymore, it's the status quo. And the modern "tech-literate" uses GitHub, LinkedIn, Venmo, Discord, TikTok, Netflix, and other services that are already attached to their identity. There is a second order impact of course, but most Americans (younger and older) don't realize that, and frankly, using the same kind of rhetoric from the Assange/Wikileaks, SOPA, and the GPG days just doesn't resonate and is out of touch.Gen X Techno-libertarianism isn't counterculture anymore, it's the status quo. And the modern "tech-literate" uses GitHub, LinkedIn, Venmo, Discord, TikTok, Netflix, and other services that are already attached to their identity. Gen X Techno-libertarianism isn't counterculture anymore, it's the status quo. And the modern "tech-literate" uses GitHub, LinkedIn, Venmo, Discord, TikTok, Netflix, and other services that are already attached to their identity. Why did you put "privacy" in scare quotes? I still haven't read any truly compelling argument, why this type of surveillance is actually effective and proportionate. This conflicts with my concerns about government crackdowns and the importance of anonymity when discussing topics that cover people who have a monopoly on violence and a tendency to use it.So it's not entirely a black/white discussion to me. So it's not entirely a black/white discussion to me. People should remain able to communicate anonymously with consenting parties, send private DMs and create private group chats, and create their own service with their own form of identity verification. * All big services are unlikely to require ID without laws, because any that does not will get refugees, or if all big services collaborate, a new service will get all refugees. * All big services are unlikely to require ID without laws, because any that does not will get refugees, or if all big services collaborate, a new service will get all refugees. I've seen people post appalling shit on fuckin LinkedIn under their own names.Strong moderation keeps Internet spaces from devolving into cesspools. Strong moderation keeps Internet spaces from devolving into cesspools. I mean, this is _literally the only thing needed_ for the Trump admin to tie real names to people criticizing $whatever. so it's not as if there is no good side to this. Or have we changed the criteria for what qualifies as "depression"? This is another case of it, honestly.> eating disordersAny sort of accurate data collection here is a recent development:https://pmc.ncbi.nlm.nih.gov/articles/PMC7575017/> never ending cat and mouse game with my kids (especially my son)Having lived this with my own, I get it. Or have we changed the criteria for what qualifies as "depression"? This is another case of it, honestly.> eating disordersAny sort of accurate data collection here is a recent development:https://pmc.ncbi.nlm.nih.gov/articles/PMC7575017/> never ending cat and mouse game with my kids (especially my son)Having lived this with my own, I get it. Or have we changed the criteria for what qualifies as "depression"? This is another case of it, honestly.> eating disordersAny sort of accurate data collection here is a recent development:https://pmc.ncbi.nlm.nih.gov/articles/PMC7575017/> never ending cat and mouse game with my kids (especially my son)Having lived this with my own, I get it. https://afsp.org/suicide-statistics/I was a child of the 90's, where the numbers were higher, where we had peak PMRC.> depression ratesHave these changed? Or have we changed the criteria for what qualifies as "depression"? This is another case of it, honestly.> eating disordersAny sort of accurate data collection here is a recent development:https://pmc.ncbi.nlm.nih.gov/articles/PMC7575017/> never ending cat and mouse game with my kids (especially my son)Having lived this with my own, I get it. I was a child of the 90's, where the numbers were higher, where we had peak PMRC.> depression ratesHave these changed? Or have we changed the criteria for what qualifies as "depression"? This is another case of it, honestly.> eating disordersAny sort of accurate data collection here is a recent development:https://pmc.ncbi.nlm.nih.gov/articles/PMC7575017/> never ending cat and mouse game with my kids (especially my son)Having lived this with my own, I get it. Or have we changed the criteria for what qualifies as "depression"? This is another case of it, honestly.> eating disordersAny sort of accurate data collection here is a recent development:https://pmc.ncbi.nlm.nih.gov/articles/PMC7575017/> never ending cat and mouse game with my kids (especially my son)Having lived this with my own, I get it. Or have we changed the criteria for what qualifies as "depression"? This is another case of it, honestly.> eating disordersAny sort of accurate data collection here is a recent development:https://pmc.ncbi.nlm.nih.gov/articles/PMC7575017/> never ending cat and mouse game with my kids (especially my son)Having lived this with my own, I get it. > eating disordersAny sort of accurate data collection here is a recent development:https://pmc.ncbi.nlm.nih.gov/articles/PMC7575017/> never ending cat and mouse game with my kids (especially my son)Having lived this with my own, I get it. Any sort of accurate data collection here is a recent development:https://pmc.ncbi.nlm.nih.gov/articles/PMC7575017/> never ending cat and mouse game with my kids (especially my son)Having lived this with my own, I get it. Having lived this with my own, I get it. And you don't mind that freedoms of all of us would be restricted as a result?And then, we keep blaming boomers for those restrictions. And then, we keep blaming boomers for those restrictions. As for "freedoms," you're not free to vote or drink alcohol below a certain age. And before the internet, minors couldn't purchase pornography, either. Some people perceive this change as a return to normal, not an egregious destruction of freedom. I am not talking about pornography or alcohol at all.I hope you are aware that requiring an ID to surf the internet leads to total censoring and self-censoring of the complete internet. There goes your privacy, anonymity, and right to free speech.If your country's regime really wanted to address pornography or alcohol, I'm pretty sure they would be able to shut it down without requiring everyone's identity. The issue is, they are just using these topics to manipulate people, and you are failing to that trap. I hope you are aware that requiring an ID to surf the internet leads to total censoring and self-censoring of the complete internet. There goes your privacy, anonymity, and right to free speech.If your country's regime really wanted to address pornography or alcohol, I'm pretty sure they would be able to shut it down without requiring everyone's identity. The issue is, they are just using these topics to manipulate people, and you are failing to that trap. If your country's regime really wanted to address pornography or alcohol, I'm pretty sure they would be able to shut it down without requiring everyone's identity. The issue is, they are just using these topics to manipulate people, and you are failing to that trap. I don't want to argue over a straw man. They are talking about it in the context of "high risk" services and social media, but not the Internet as such. I think the solution we really need is age verification for table saws. Of course, it goes without saying that the saw should also monitor the user's cuts to make sure they're connected with the right national suppliers who can supply material to meet their needs, and to ensure that you aren't using the saw to cut any inappropriate materials from unregistered sources. Usually the people who say things like that really just want to restrict everyone's freedoms. You may be failing to comprehend the concept of "freedom". "I'm the smartest guy here" is not an argument. It's just something an NPC would say when they run out of arguments.PS: This is not ad hominem. "I'm the smartest guy here" is not an argument. It's just something an NPC would say when they run out of arguments.PS: This is not ad hominem. They've been deciding what "freedom" is for a long time (even deciding what constitutional rights are, on occasion, see ATF bureaucrats constantly publishing and changing rules re-deciding what constitutional restraints they think there are on the 2A).Of course, these "scientist and lawyers" know they have this power, and are so seeped in it, they occasionally forget when they step out of the ivory tower that the plebs (and indeed, the foundational ideals USA was built on written by those such as Locke) usually either disagree with it or aren't aware that much of the USA functions under "credentialism/technocrat makes right" and the scientist and the lawyer as the arbiter of freedom.This feels like one of those moments when the technocrats forget that they've shed the thin façade they hide behind. This feels like one of those moments when the technocrats forget that they've shed the thin façade they hide behind. I'll get my simpleminded ass out of here leave this discussion to the scientists. You mean that you shirk your responsibility to teach your child how to protect themself on the Internet, and instead trust the faceless corp to limit their access at the cost of everyone's privacy? Heck, you can't even obtain housing -- which is an essential service -- without having to provide identity in most cases. What remains to be seen is if the outcome of teenagers becoming social pariahs is really worse than the alternatives. It's about surveillance and a chilling effect on speech. LOL.Of course these technologies keep existing, and you end up with the worst, most wretched people implementing them, and we're all worse off. Concretely, few people are working on ZKPs for age verification because the hive mind of "good people" who know what ZKPs are make working on age verification social anathema. Of course these technologies keep existing, and you end up with the worst, most wretched people implementing them, and we're all worse off. Concretely, few people are working on ZKPs for age verification because the hive mind of "good people" who know what ZKPs are make working on age verification social anathema. Just make Google/Apple reveal part of that data (age > x years) to websites and apps.Boom, done. I absolutely hate the Nirvana fallacy that you people think is acceptable here, while hundreds of millions of kids suffer from serious developmental issues, as reported left and right by all kinds of organizations and governments themselves. Maybe TBL is right and we need a new internet? I don't have the answer here, but this one is too commercialized and these companies are very hawkish. Big tech don't have wait for an outright government ban when they can just say that we are a teen-only site by default and everyone have to verify if they are over 18 or not. This age verification will affect everyone no matter what. Once you are verified, you just flip a bit "verified" in the database and delete all identification data.No reason to store the data indefinitely I think most people are aligned here, and that an internet without identification is inevitable whether we like it or not. Identification fixes nothing here, you log with your account, plug in the AI.The problems with social media have nothing to do with ID and everything to do with godawful incentives, the argument seems to be that it's a large price to pay but that it's worth it. The end result is absolutely terrible either way The end result is absolutely terrible either way While I am not against internet ID, there is a case to be made for social media for the harms they are causing. This is impossible now and it will be impossible once ID check becomes ubiquitous.3) I will be happy to see (or not) a blue checkmark by the profile name. 3) I will be happy to see (or not) a blue checkmark by the profile name. Like everything else in society, there are tradeoffs here, I'm much more concerned with the damage done to children's developing brains than I am to violations of data privacy, so I'm okay with age verification, however draconian it may be. Our middle child (aged 12) has an Android phone, but it has Family Link on it.Nominally he gets 60 mins of phone time per day, but he rarely even comes close to that, according to Family Link he used it for a total of 17 minutes yesterday. One comes to the conclusion that with no social media apps, the phone just isn't that attractive.He seems to spend most of his spare time reading or playing sports... Nominally he gets 60 mins of phone time per day, but he rarely even comes close to that, according to Family Link he used it for a total of 17 minutes yesterday. One comes to the conclusion that with no social media apps, the phone just isn't that attractive.He seems to spend most of his spare time reading or playing sports... He seems to spend most of his spare time reading or playing sports... If it's a concern, parents can prevent or limit their children's use. If all this were being done to prevent consistent successful terrorist attacks in the US with tens of thousands of annual casualties, I'd say okay maybe there is an unavoidable trade-off that must be made here, but this is so absurd. No we do not.>I don't want to live in a world where the average person unknowingly interacts with bots more than other individuals and where black market actors can sway public opinion with armies of bots.That is not the argument for identification on many places on the internet. The companies that go along with all this don't want to get rid of all bots and public opinion campaigns. >I don't want to live in a world where the average person unknowingly interacts with bots more than other individuals and where black market actors can sway public opinion with armies of bots.That is not the argument for identification on many places on the internet. The companies that go along with all this don't want to get rid of all bots and public opinion campaigns. The companies that go along with all this don't want to get rid of all bots and public opinion campaigns. At any point they can tell a real human what they can and can't say, and if they go against their masters, their "real human" status is revoked, because you trust the platform and not the person.If we want to go full conspiritard, we could accuse those of wanting to control speech to be the financial backers of those flooding social media with AI slop: https://www.youtube.com/watch?v=-gGLvg0n-uY -- this fictional video thematically marries Metal Gear Solid 2's plot with current events: "perfect AI speech, audio and video synthesis will drown out reality [...] That is when we will present our solution: mandatory digital identity verification for all humans at all times" If we want to go full conspiritard, we could accuse those of wanting to control speech to be the financial backers of those flooding social media with AI slop: https://www.youtube.com/watch?v=-gGLvg0n-uY -- this fictional video thematically marries Metal Gear Solid 2's plot with current events: "perfect AI speech, audio and video synthesis will drown out reality [...] That is when we will present our solution: mandatory digital identity verification for all humans at all times" The various government actions trying to force "robust" age verification on the internet are being woefully naive in trusting other internet companies and letting them skirt existing laws on data protection.That's not even mentioning other factions whose real goal is in shutting down legal speech that doesn't meet their Christian agenda: https://theintercept.com/2024/08/16/project-2025-russ-vought...You are being a useful idiot, sorry. Your weakness is what politicians exploit when they say "think of the children", you fail to see the amoral power-grabs hiding beneath their professed sentiment.I don't want you encouraging people to demand my identity because you trust "authorities" taking yours That's not even mentioning other factions whose real goal is in shutting down legal speech that doesn't meet their Christian agenda: https://theintercept.com/2024/08/16/project-2025-russ-vought...You are being a useful idiot, sorry. Your weakness is what politicians exploit when they say "think of the children", you fail to see the amoral power-grabs hiding beneath their professed sentiment.I don't want you encouraging people to demand my identity because you trust "authorities" taking yours Your weakness is what politicians exploit when they say "think of the children", you fail to see the amoral power-grabs hiding beneath their professed sentiment.I don't want you encouraging people to demand my identity because you trust "authorities" taking yours Why don't we have PKI built in to our birth certificates and drivers licenses? Plus what you're asking would require international id verification for everyone, which would first mostly make those IDs a lot cheaper. Just try to discuss anything about Russia, or how bad some specific decision of the Chinese CCP is. Or, if you're so inclined: think about how having this in the US would mean Trump would be authorizing bot armies.This exists within China, by the way, and I guarantee you: it did not result in honest online discussion about goods, services or politics. This exists within China, by the way, and I guarantee you: it did not result in honest online discussion about goods, services or politics. Unfortunately, "well what if there was a magic amulet that held the truth of the user's age and we could talk to it" is not a worthwhile path to explore. In an age of data leaks, identity theft, and phishing, we are training users to constantly present their ID, and critically for things as low stakes as facebook. It would be one thing if we were training people to show their ID JUST for filing taxes online or something (still not great, but at least conveys the sensitivity of the information they are releasing), but no, we are saying that the "correct future" is handing this information out for Farmville (and we can expect its requirement to expand over time of course). It doesn't matter if it happens at the OS level or the web page level -- they are identical as far as phishing is concerned. You spoof the UI that the OS would bring up to scan your face or ID or whatever, and everyone is trained to just grant the information, just like we're all used to just hitting "OK" and don't bother reading dialogs anymore.2. Seems like a great way for tech companies to gain leverage over smaller third world companies by controlling their access to the internet to implementing support for their government documents. Also seems like a great way to lock open source out of serious operating system development if it now requires relationships with all the countries in the world. If you think this is "just" a problem of getting IDs into everyone's hands, remember that it a common practice to take foreign worker's passports and IDs away from them in order to hold them effectively hostage. Short of implementing HDCP-style hardware attestation (which more or less locks in the current players indefinitely), this will be trivially circumvented by the parties you're attempting to help, much like DRM was.Again, the issues that these systems are attempting to address are valid, I am not saying otherwise. The temptation to just have an oracle gate-checker is tempting, I know. But we've seen time and again that this just (at best) creates a lot of work and doesn't actually solve the problem. Look no further than cookie banners -- nothing has changed from a data collection perspective, it's just created a "cookie banner expert" industry and possibly made users more indifferent to data collection as a knee-jerk reaction to the UX decay banners have created on the internet as a whole. Let's not 10 years from now laugh about how any sufficiently motivated teenager can scan their parent's phone while they're asleep, or pay some deadbeat 18 year-old to use their ID, and bypass any verification system, while simulateneously furthering the stranglehold large corporations have over the internet. In an age of data leaks, identity theft, and phishing, we are training users to constantly present their ID, and critically for things as low stakes as facebook. It would be one thing if we were training people to show their ID JUST for filing taxes online or something (still not great, but at least conveys the sensitivity of the information they are releasing), but no, we are saying that the "correct future" is handing this information out for Farmville (and we can expect its requirement to expand over time of course). It doesn't matter if it happens at the OS level or the web page level -- they are identical as far as phishing is concerned. You spoof the UI that the OS would bring up to scan your face or ID or whatever, and everyone is trained to just grant the information, just like we're all used to just hitting "OK" and don't bother reading dialogs anymore.2. Seems like a great way for tech companies to gain leverage over smaller third world companies by controlling their access to the internet to implementing support for their government documents. Also seems like a great way to lock open source out of serious operating system development if it now requires relationships with all the countries in the world. If you think this is "just" a problem of getting IDs into everyone's hands, remember that it a common practice to take foreign worker's passports and IDs away from them in order to hold them effectively hostage. Short of implementing HDCP-style hardware attestation (which more or less locks in the current players indefinitely), this will be trivially circumvented by the parties you're attempting to help, much like DRM was.Again, the issues that these systems are attempting to address are valid, I am not saying otherwise. The temptation to just have an oracle gate-checker is tempting, I know. But we've seen time and again that this just (at best) creates a lot of work and doesn't actually solve the problem. Look no further than cookie banners -- nothing has changed from a data collection perspective, it's just created a "cookie banner expert" industry and possibly made users more indifferent to data collection as a knee-jerk reaction to the UX decay banners have created on the internet as a whole. Let's not 10 years from now laugh about how any sufficiently motivated teenager can scan their parent's phone while they're asleep, or pay some deadbeat 18 year-old to use their ID, and bypass any verification system, while simulateneously furthering the stranglehold large corporations have over the internet. Seems like a great way for tech companies to gain leverage over smaller third world companies by controlling their access to the internet to implementing support for their government documents. Also seems like a great way to lock open source out of serious operating system development if it now requires relationships with all the countries in the world. If you think this is "just" a problem of getting IDs into everyone's hands, remember that it a common practice to take foreign worker's passports and IDs away from them in order to hold them effectively hostage. Short of implementing HDCP-style hardware attestation (which more or less locks in the current players indefinitely), this will be trivially circumvented by the parties you're attempting to help, much like DRM was.Again, the issues that these systems are attempting to address are valid, I am not saying otherwise. The temptation to just have an oracle gate-checker is tempting, I know. But we've seen time and again that this just (at best) creates a lot of work and doesn't actually solve the problem. Look no further than cookie banners -- nothing has changed from a data collection perspective, it's just created a "cookie banner expert" industry and possibly made users more indifferent to data collection as a knee-jerk reaction to the UX decay banners have created on the internet as a whole. Let's not 10 years from now laugh about how any sufficiently motivated teenager can scan their parent's phone while they're asleep, or pay some deadbeat 18 year-old to use their ID, and bypass any verification system, while simulateneously furthering the stranglehold large corporations have over the internet. Short of implementing HDCP-style hardware attestation (which more or less locks in the current players indefinitely), this will be trivially circumvented by the parties you're attempting to help, much like DRM was.Again, the issues that these systems are attempting to address are valid, I am not saying otherwise. The temptation to just have an oracle gate-checker is tempting, I know. But we've seen time and again that this just (at best) creates a lot of work and doesn't actually solve the problem. Look no further than cookie banners -- nothing has changed from a data collection perspective, it's just created a "cookie banner expert" industry and possibly made users more indifferent to data collection as a knee-jerk reaction to the UX decay banners have created on the internet as a whole. Let's not 10 years from now laugh about how any sufficiently motivated teenager can scan their parent's phone while they're asleep, or pay some deadbeat 18 year-old to use their ID, and bypass any verification system, while simulateneously furthering the stranglehold large corporations have over the internet. The temptation to just have an oracle gate-checker is tempting, I know. But we've seen time and again that this just (at best) creates a lot of work and doesn't actually solve the problem. Look no further than cookie banners -- nothing has changed from a data collection perspective, it's just created a "cookie banner expert" industry and possibly made users more indifferent to data collection as a knee-jerk reaction to the UX decay banners have created on the internet as a whole. Let's not 10 years from now laugh about how any sufficiently motivated teenager can scan their parent's phone while they're asleep, or pay some deadbeat 18 year-old to use their ID, and bypass any verification system, while simulateneously furthering the stranglehold large corporations have over the internet. 2) Discord asks (state system) for an age validation.3) In pop up window, state validates the persons age with ID matching with face recognition.3) State system sends token to discord with yes or no with zero data retention in the state records.4) Discord takes action on the account.What is so hard about this? 3) In pop up window, state validates the persons age with ID matching with face recognition.3) State system sends token to discord with yes or no with zero data retention in the state records.4) Discord takes action on the account.What is so hard about this? 3) State system sends token to discord with yes or no with zero data retention in the state records.4) Discord takes action on the account.What is so hard about this? 4) Discord takes action on the account.What is so hard about this? Your system seems to address none of the issues I listed. Congrats, I can now trivially make a pop up a window that looks like this UI and use it to steal your info, as the user will just respond on auto-drive, as we have repeatedly shown both in user studies and in our own lived experiences. I also explained how a system like this would assist in the practice of trapping migrant workers by confiscating their government credentials [1]. This is a huge problem today in Asia, and one of the few outlets captive workers can use to escape this control is the internet -- a "loophole" your system would dutifully close for these corporations.I am happy to have a discussion about this -- it's how we come up with new solutions! There's tons of articles about this, here is one of the first ones that comes up on Google: https://www.amnesty.org/en/latest/news/2025/05/saudi-arabia-... I am happy to have a discussion about this -- it's how we come up with new solutions! There's tons of articles about this, here is one of the first ones that comes up on Google: https://www.amnesty.org/en/latest/news/2025/05/saudi-arabia-... There's tons of articles about this, here is one of the first ones that comes up on Google: https://www.amnesty.org/en/latest/news/2025/05/saudi-arabia-... Basically, kids can sign up for an account triggering a notification to parents. Gets parental restrictions in the login flow without making it a PITA. and if you have internet access without paying, that means someone else is legally responsible for your access"problem solved" ? I'm not for these draconian age verification nonsense, but this isn't a valid argument. This is the way it works with e.g. alcohol and cigarettes, most places. Famously kids can just get a beer from a random fridge and chug it, but someone 16/18/21+ will be responsible and everyone seems mostly fine with this. I regularly talk to other parents at the school gates who have no idea that permissions on mobiles even exist, let alone that they can choose what they let each app have access to.The general public people just dont care. (fwiw I regularly talk to parents who are quite aware of various parental controls and use them effectively, combined with talking to their kids and just general good parenting practices) Is it bypassable by a sufficiently determined child? Yes, but so it is the current age verification nonsense. just like you already are responsible for what happens on your free public network (torrenting, hacking, CSAM, etc.) in most jurisdictions(for what its worth, i think age verification is dumb. (for what its worth, i think age verification is dumb. That being said nothing about these laws is about protecting children; their primary purpose is to crack down on the next Just Stop Oil or Palestine Action so for that reason should be opposed. I could check in the back of my parents' closet (hidden under some fabric) for at least a decade's worth of dirty magazines. > That can't be healthy.The only thing that's unhealthy is not being able to talk frankly and honestly about sex and sexuality with your peers, parents, and other important adults in your life. For you'll need to be accounted while they do the counting. Instead of requiring IDs, we should let parents manage what their children do online. -Everyone keeps assuming that Discord / Twitch / Snapchat are being forced to do this. But that's not the game.There are many ways in which such a system could be implemented. They could have asked people to use a credit card. Adult entertainment services have been using this as a way to do tacit age verification for a very long time now. Or, they could have made a new zero-knowledge proof system. Or, ideally, they could have told the authorities to get bent. †Tech is hardly the first industry to face significant (justifiable or unjustifiable) government backlash. I am hesitant to use them as examples as they're a net harm, whereas this is about preventing a societal net harm, but the fossil fuel and tobacco industries fought their governments for decades and straight up changed the political system to suit them.FAANG are richer than they ever were. Even Discord can raise more and deploy more capital than most of the tobacco industry at the time. A cause most people can get behind (see: privacy as a selling point for Apple and the backlash to Ring). They're leaning into it.Let's take a look at what they're asking from people for a second, the face scan, If you choose Facial Age Estimation, you'll be prompted to record a short video selfie of your face. The Facial Age Estimation technology runs entirely on your device in real time when you are performing the verification. This is not just "take a selfie" – they're getting the user to move the device laterally to extract facial structure. never leaves the device, but that doesn't mean the biometric data isn't extracted and sent to their third-party supplier, k-Id. instead, it sends a bunch of metadata about your face and general process details. The author assumes that "this [approach] is good for your privacy." If you give me the depth data for a face, you've given me the fingerprint for that face. Discord is also doing profiling along vectors (presumably behavioral and demographic features) which the author describes as, after some trial and error, we narrowed the checked part to the prediction arrays, which are outputs, primaryOutputs and raws. turns out, both outputs and primaryOutputs are generated from raws. basically, the raw numbers are mapped to age outputs, and then the outliers get removed with z-score (once for primaryOutputs and twice for outputs). Discord plugs into games and allows people to share what they're doing with their friends. For example, Discord can automatically share which song a user is listening on Spotify with their friends (who can join in), the game they're playing, whether they're streaming on Twitch etc. Discord also has data about your voice (which they say they may store) and now your face.Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. Everyone keeps assuming that Discord / Twitch / Snapchat are being forced to do this. But that's not the game.There are many ways in which such a system could be implemented. They could have asked people to use a credit card. Adult entertainment services have been using this as a way to do tacit age verification for a very long time now. Or, they could have made a new zero-knowledge proof system. Or, ideally, they could have told the authorities to get bent. †Tech is hardly the first industry to face significant (justifiable or unjustifiable) government backlash. I am hesitant to use them as examples as they're a net harm, whereas this is about preventing a societal net harm, but the fossil fuel and tobacco industries fought their governments for decades and straight up changed the political system to suit them.FAANG are richer than they ever were. Even Discord can raise more and deploy more capital than most of the tobacco industry at the time. A cause most people can get behind (see: privacy as a selling point for Apple and the backlash to Ring). They're leaning into it.Let's take a look at what they're asking from people for a second, the face scan, If you choose Facial Age Estimation, you'll be prompted to record a short video selfie of your face. The Facial Age Estimation technology runs entirely on your device in real time when you are performing the verification. This is not just "take a selfie" – they're getting the user to move the device laterally to extract facial structure. never leaves the device, but that doesn't mean the biometric data isn't extracted and sent to their third-party supplier, k-Id. instead, it sends a bunch of metadata about your face and general process details. The author assumes that "this [approach] is good for your privacy." If you give me the depth data for a face, you've given me the fingerprint for that face. Discord is also doing profiling along vectors (presumably behavioral and demographic features) which the author describes as, after some trial and error, we narrowed the checked part to the prediction arrays, which are outputs, primaryOutputs and raws. turns out, both outputs and primaryOutputs are generated from raws. basically, the raw numbers are mapped to age outputs, and then the outliers get removed with z-score (once for primaryOutputs and twice for outputs). Discord plugs into games and allows people to share what they're doing with their friends. For example, Discord can automatically share which song a user is listening on Spotify with their friends (who can join in), the game they're playing, whether they're streaming on Twitch etc. Discord also has data about your voice (which they say they may store) and now your face.Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. There are many ways in which such a system could be implemented. They could have asked people to use a credit card. Adult entertainment services have been using this as a way to do tacit age verification for a very long time now. Or, they could have made a new zero-knowledge proof system. Or, ideally, they could have told the authorities to get bent. †Tech is hardly the first industry to face significant (justifiable or unjustifiable) government backlash. I am hesitant to use them as examples as they're a net harm, whereas this is about preventing a societal net harm, but the fossil fuel and tobacco industries fought their governments for decades and straight up changed the political system to suit them.FAANG are richer than they ever were. Even Discord can raise more and deploy more capital than most of the tobacco industry at the time. A cause most people can get behind (see: privacy as a selling point for Apple and the backlash to Ring). They're leaning into it.Let's take a look at what they're asking from people for a second, the face scan, If you choose Facial Age Estimation, you'll be prompted to record a short video selfie of your face. The Facial Age Estimation technology runs entirely on your device in real time when you are performing the verification. This is not just "take a selfie" – they're getting the user to move the device laterally to extract facial structure. never leaves the device, but that doesn't mean the biometric data isn't extracted and sent to their third-party supplier, k-Id. instead, it sends a bunch of metadata about your face and general process details. The author assumes that "this [approach] is good for your privacy." If you give me the depth data for a face, you've given me the fingerprint for that face. Discord is also doing profiling along vectors (presumably behavioral and demographic features) which the author describes as, after some trial and error, we narrowed the checked part to the prediction arrays, which are outputs, primaryOutputs and raws. turns out, both outputs and primaryOutputs are generated from raws. basically, the raw numbers are mapped to age outputs, and then the outliers get removed with z-score (once for primaryOutputs and twice for outputs). Discord plugs into games and allows people to share what they're doing with their friends. For example, Discord can automatically share which song a user is listening on Spotify with their friends (who can join in), the game they're playing, whether they're streaming on Twitch etc. Discord also has data about your voice (which they say they may store) and now your face.Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. Tech is hardly the first industry to face significant (justifiable or unjustifiable) government backlash. I am hesitant to use them as examples as they're a net harm, whereas this is about preventing a societal net harm, but the fossil fuel and tobacco industries fought their governments for decades and straight up changed the political system to suit them.FAANG are richer than they ever were. A cause most people can get behind (see: privacy as a selling point for Apple and the backlash to Ring). They're leaning into it.Let's take a look at what they're asking from people for a second, the face scan, If you choose Facial Age Estimation, you'll be prompted to record a short video selfie of your face. The Facial Age Estimation technology runs entirely on your device in real time when you are performing the verification. This is not just "take a selfie" – they're getting the user to move the device laterally to extract facial structure. never leaves the device, but that doesn't mean the biometric data isn't extracted and sent to their third-party supplier, k-Id. instead, it sends a bunch of metadata about your face and general process details. The author assumes that "this [approach] is good for your privacy." If you give me the depth data for a face, you've given me the fingerprint for that face. Discord is also doing profiling along vectors (presumably behavioral and demographic features) which the author describes as, after some trial and error, we narrowed the checked part to the prediction arrays, which are outputs, primaryOutputs and raws. turns out, both outputs and primaryOutputs are generated from raws. basically, the raw numbers are mapped to age outputs, and then the outliers get removed with z-score (once for primaryOutputs and twice for outputs). Discord plugs into games and allows people to share what they're doing with their friends. For example, Discord can automatically share which song a user is listening on Spotify with their friends (who can join in), the game they're playing, whether they're streaming on Twitch etc. Discord also has data about your voice (which they say they may store) and now your face.Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. A cause most people can get behind (see: privacy as a selling point for Apple and the backlash to Ring). They're leaning into it.Let's take a look at what they're asking from people for a second, the face scan, If you choose Facial Age Estimation, you'll be prompted to record a short video selfie of your face. The Facial Age Estimation technology runs entirely on your device in real time when you are performing the verification. This is not just "take a selfie" – they're getting the user to move the device laterally to extract facial structure. never leaves the device, but that doesn't mean the biometric data isn't extracted and sent to their third-party supplier, k-Id. instead, it sends a bunch of metadata about your face and general process details. The author assumes that "this [approach] is good for your privacy." If you give me the depth data for a face, you've given me the fingerprint for that face. Discord is also doing profiling along vectors (presumably behavioral and demographic features) which the author describes as, after some trial and error, we narrowed the checked part to the prediction arrays, which are outputs, primaryOutputs and raws. turns out, both outputs and primaryOutputs are generated from raws. basically, the raw numbers are mapped to age outputs, and then the outliers get removed with z-score (once for primaryOutputs and twice for outputs). Discord plugs into games and allows people to share what they're doing with their friends. For example, Discord can automatically share which song a user is listening on Spotify with their friends (who can join in), the game they're playing, whether they're streaming on Twitch etc. Discord also has data about your voice (which they say they may store) and now your face.Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. Let's take a look at what they're asking from people for a second, the face scan, If you choose Facial Age Estimation, you'll be prompted to record a short video selfie of your face. The Facial Age Estimation technology runs entirely on your device in real time when you are performing the verification. This is not just "take a selfie" – they're getting the user to move the device laterally to extract facial structure. never leaves the device, but that doesn't mean the biometric data isn't extracted and sent to their third-party supplier, k-Id. instead, it sends a bunch of metadata about your face and general process details. The author assumes that "this [approach] is good for your privacy." If you give me the depth data for a face, you've given me the fingerprint for that face. Discord is also doing profiling along vectors (presumably behavioral and demographic features) which the author describes as, after some trial and error, we narrowed the checked part to the prediction arrays, which are outputs, primaryOutputs and raws. turns out, both outputs and primaryOutputs are generated from raws. basically, the raw numbers are mapped to age outputs, and then the outliers get removed with z-score (once for primaryOutputs and twice for outputs). Discord plugs into games and allows people to share what they're doing with their friends. For example, Discord can automatically share which song a user is listening on Spotify with their friends (who can join in), the game they're playing, whether they're streaming on Twitch etc. Discord also has data about your voice (which they say they may store) and now your face.Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. The Facial Age Estimation technology runs entirely on your device in real time when you are performing the verification. This is not just "take a selfie" – they're getting the user to move the device laterally to extract facial structure. never leaves the device, but that doesn't mean the biometric data isn't extracted and sent to their third-party supplier, k-Id. instead, it sends a bunch of metadata about your face and general process details. The author assumes that "this [approach] is good for your privacy." If you give me the depth data for a face, you've given me the fingerprint for that face. Discord is also doing profiling along vectors (presumably behavioral and demographic features) which the author describes as, after some trial and error, we narrowed the checked part to the prediction arrays, which are outputs, primaryOutputs and raws. turns out, both outputs and primaryOutputs are generated from raws. basically, the raw numbers are mapped to age outputs, and then the outliers get removed with z-score (once for primaryOutputs and twice for outputs). Discord plugs into games and allows people to share what they're doing with their friends. For example, Discord can automatically share which song a user is listening on Spotify with their friends (who can join in), the game they're playing, whether they're streaming on Twitch etc. Discord also has data about your voice (which they say they may store) and now your face.Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. instead, it sends a bunch of metadata about your face and general process details. The author assumes that "this [approach] is good for your privacy." If you give me the depth data for a face, you've given me the fingerprint for that face. Discord is also doing profiling along vectors (presumably behavioral and demographic features) which the author describes as, after some trial and error, we narrowed the checked part to the prediction arrays, which are outputs, primaryOutputs and raws. turns out, both outputs and primaryOutputs are generated from raws. basically, the raw numbers are mapped to age outputs, and then the outliers get removed with z-score (once for primaryOutputs and twice for outputs). Discord plugs into games and allows people to share what they're doing with their friends. For example, Discord can automatically share which song a user is listening on Spotify with their friends (who can join in), the game they're playing, whether they're streaming on Twitch etc. Discord also has data about your voice (which they say they may store) and now your face.Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. after some trial and error, we narrowed the checked part to the prediction arrays, which are outputs, primaryOutputs and raws. turns out, both outputs and primaryOutputs are generated from raws. basically, the raw numbers are mapped to age outputs, and then the outliers get removed with z-score (once for primaryOutputs and twice for outputs). Discord plugs into games and allows people to share what they're doing with their friends. For example, Discord can automatically share which song a user is listening on Spotify with their friends (who can join in), the game they're playing, whether they're streaming on Twitch etc. Discord also has data about your voice (which they say they may store) and now your face.Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. Is some or all of this data being turned into features that are being fed to this third-party k-ID? With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. https://www.techinasia.com/a16z-lightspeed-bet-singapore-par...k-ID is (at first glance) extracting fairly similar data from Snapchat, Twitch etc. With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. k-ID is (at first glance) extracting fairly similar data from Snapchat, Twitch etc. With ID documents added into the mix, this certainly seems like a very interesting global profiling dataset backstopped with government documentation as ground truth. :)† like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. † like they already have for algorithmic social media and profiling, https://www.newyorker.com/magazine/2024/10/14/silicon-valley...Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. Somehow there's tens to hundreds of millions available for crypto causes and algorithmic social media crusades, but there's none for the "existential threat" of age verification. We should focus on teaching parents how to educate their children properly, and teach children how to safely browse the internet and how to avoid common scams and pitfalls.I played Roblox when I was a teenager and all the time my aunt told me to be careful of who I talked to online, as they could be a pedo. Even though there wasn't a constant monitoring from my parents or family, her words were repeated many times that I actually thought 5 times before sharing any kind of personal information online, back then. I played Roblox when I was a teenager and all the time my aunt told me to be careful of who I talked to online, as they could be a pedo. Even though there wasn't a constant monitoring from my parents or family, her words were repeated many times that I actually thought 5 times before sharing any kind of personal information online, back then. nope, they are going after dissenters, not bad guys. The advantage, I think, of age verification by private companies over cellphone bans in public schools is that cellphone bans appear as a line-item on the government balance sheet, whereas the costs of age verification are diffuse and difficult to calculate. It's actually quite common for governments to prefer imposing costs in ways that make it easier for the legislators to throw up their hands and whistle innocently about why everything just got more expensive and difficult.And the argument over age verification for merely viewing websites, which is technically difficult and invasive, muddles the waters over the question of age verification for social media profiles, where underage users are more likely to get caught and banned by simple observation. It seems like technology has caused people to believe that the law has to be perfectly enforceable in order to be any good, but that isn't historically how the law has worked -- it is possible for most crimes to go unsolved and yet most criminals get caught. And the argument over age verification for merely viewing websites, which is technically difficult and invasive, muddles the waters over the question of age verification for social media profiles, where underage users are more likely to get caught and banned by simple observation. It seems like technology has caused people to believe that the law has to be perfectly enforceable in order to be any good, but that isn't historically how the law has worked -- it is possible for most crimes to go unsolved and yet most criminals get caught. Allowing children to see gore and extreme porn at a young age is not healthy. And then we have all the "trading" platforms (gambling).Even though my brothers were able to get many hard drugs when I was young, around 1977, there was a lot of friction. Some bars would not card us but even then there was risk and sometimes they got caught. In NY we could buy cigarettes, no friction, and the one drug I took when I was young, addicted to them at 16, finally quitting for good at 20. They are doing this with guns right now, big trial is just finishing and it looks like a father who gave his kid an ak47 at 13 is about to go to jail.I would like to see a state ID program when the ID is just verified by the State ID system. Sites like Discord could just get a OK signal from the state system. They could use facial recognition on the phone that would match it with the ID.Something needs to be done however. You do not need an ID to walk into a library, but you need one to get into a strip club. Even though my brothers were able to get many hard drugs when I was young, around 1977, there was a lot of friction. Some bars would not card us but even then there was risk and sometimes they got caught. In NY we could buy cigarettes, no friction, and the one drug I took when I was young, addicted to them at 16, finally quitting for good at 20. They are doing this with guns right now, big trial is just finishing and it looks like a father who gave his kid an ak47 at 13 is about to go to jail.I would like to see a state ID program when the ID is just verified by the State ID system. Sites like Discord could just get a OK signal from the state system. They could use facial recognition on the phone that would match it with the ID.Something needs to be done however. You do not need an ID to walk into a library, but you need one to get into a strip club. They are doing this with guns right now, big trial is just finishing and it looks like a father who gave his kid an ak47 at 13 is about to go to jail.I would like to see a state ID program when the ID is just verified by the State ID system. Sites like Discord could just get a OK signal from the state system. They could use facial recognition on the phone that would match it with the ID.Something needs to be done however. You do not need an ID to walk into a library, but you need one to get into a strip club. Sites like Discord could just get a OK signal from the state system. They could use facial recognition on the phone that would match it with the ID.Something needs to be done however. You do not need an ID to walk into a library, but you need one to get into a strip club. You do not need an ID to walk into a library, but you need one to get into a strip club. It's not like social media starts being a positive in our life at 20. The way these companies do social media is harmful to mental health at every age. This is solving the wrong problem.The solution is to take away their levers to make the system so addictive. A nice space to keep in touch with your friends. A nice space to keep in touch with your friends. I don't think this legislation would have helped me. I stayed off social media entirely in college. Even with nobody at all in my social sphere, it was still addicting. There are too many sites out there that won't comply and I was too technically savvy to not attempt to bypass any guardrails.The issue in my case was not one of "watching this material hurt me" in and of itself. They already punished me severely for mundane things and I did not want to be willingly subjected to more. And I carried a level of shame and disgust so I never felt comfortable disclosing my addiction to any school counselors or therapists for decades. The stigma around sexual issues preventing people from talking about them has only grown worse in the ensuing years, unfortunately.At most this kind of policy will force teenagers off platforms like Discord which might help with being matched with strangers, but there are still other avenues for this. You cannot prevent children from viewing porn online. You cannot lock down the entire Internet. You can only be honest with your children and not blame or reproach them for the issues they have to deal with like mine did.In my opinion, given that my parents were fundamentally unsafe people to talk to, causing me to think that all people were unsafe, then the issue of pornography exposure became an issue. In my case, I do not believe there was any hope for me that additional legislation or restrictions could provide, outside of waking up to my abuse and my sex addiction as an adult decades later. In life, things like those just happen sometimes. The debate we're having here on this tech-focused site is going to pass by them unnoticed. They're not going to seriously consider these issues and the status quo will continue. They won't talk with their children to see if everything's okay. I don't have many suggestions to offer except "find your best family," even if they aren't blood related. They already punished me severely for mundane things and I did not want to be willingly subjected to more. And I carried a level of shame and disgust so I never felt comfortable disclosing my addiction to any school counselors or therapists for decades. The stigma around sexual issues preventing people from talking about them has only grown worse in the ensuing years, unfortunately.At most this kind of policy will force teenagers off platforms like Discord which might help with being matched with strangers, but there are still other avenues for this. You cannot prevent children from viewing porn online. You cannot lock down the entire Internet. You can only be honest with your children and not blame or reproach them for the issues they have to deal with like mine did.In my opinion, given that my parents were fundamentally unsafe people to talk to, causing me to think that all people were unsafe, then the issue of pornography exposure became an issue. In my case, I do not believe there was any hope for me that additional legislation or restrictions could provide, outside of waking up to my abuse and my sex addiction as an adult decades later. In life, things like those just happen sometimes. The debate we're having here on this tech-focused site is going to pass by them unnoticed. They're not going to seriously consider these issues and the status quo will continue. They won't talk with their children to see if everything's okay. I don't have many suggestions to offer except "find your best family," even if they aren't blood related. At most this kind of policy will force teenagers off platforms like Discord which might help with being matched with strangers, but there are still other avenues for this. You cannot prevent children from viewing porn online. You cannot lock down the entire Internet. You can only be honest with your children and not blame or reproach them for the issues they have to deal with like mine did.In my opinion, given that my parents were fundamentally unsafe people to talk to, causing me to think that all people were unsafe, then the issue of pornography exposure became an issue. In my case, I do not believe there was any hope for me that additional legislation or restrictions could provide, outside of waking up to my abuse and my sex addiction as an adult decades later. In life, things like those just happen sometimes. The debate we're having here on this tech-focused site is going to pass by them unnoticed. They're not going to seriously consider these issues and the status quo will continue. They won't talk with their children to see if everything's okay. I don't have many suggestions to offer except "find your best family," even if they aren't blood related. In my opinion, given that my parents were fundamentally unsafe people to talk to, causing me to think that all people were unsafe, then the issue of pornography exposure became an issue. In my case, I do not believe there was any hope for me that additional legislation or restrictions could provide, outside of waking up to my abuse and my sex addiction as an adult decades later. In life, things like those just happen sometimes. The debate we're having here on this tech-focused site is going to pass by them unnoticed. They're not going to seriously consider these issues and the status quo will continue. They won't talk with their children to see if everything's okay. I don't have many suggestions to offer except "find your best family," even if they aren't blood related. I believe many parents who need to think about this issue simply won't. The debate we're having here on this tech-focused site is going to pass by them unnoticed. They're not going to seriously consider these issues and the status quo will continue. They won't talk with their children to see if everything's okay. I don't have many suggestions to offer except "find your best family," even if they aren't blood related. Tradeoff acknowledged, and this runs both sides, there's hundreds of risks that these policies are addressing.To mention a specific one, I was exposed to pornography online at age 9 which is obviously an issue, the incumbent system allowed this to happen and will continue to do so. So to what tradeoffs in policy do detractors of age verification think are so terrible that it's more important than avoiding, for example, allowing kids first sexual experiences to be pornography. Is that equivalent?Or, what alternative solutions are counter-proposed to avoid these issues without age verification and vpn bans.Note 2 things before responding:1)per the original quote, it is not valid to ignore the trade offs with arguments like "child abuse is an excuse to install civilian control by governments"2) this was not your initiave, another group is the one making huge efforts to intervene and change the status quo, so whatever solution is counterproposed needs to be new, otherwise, as an existing solution, it was therefore ineffective.If any of those is your argument, you are not part of the conversation, you have failed to act as wardens of the internet, and whatever systems you control will be slowly removed from you by authorities and technical professionals that follow the regulations. Whatever crumbs you are left as an admin, will be relegated to increasingly niche crypto communities where you will be pooled with dissidents and criminals of types you will need to either ignore or pretend are ok. You will create a new Tor, a Gab, a Conservapedia, a HackerForums, and you will be hunted by the obvious and inequivocal right side of the law. The notion of right and wrong which is like totally subjective anyways? So to what tradeoffs in policy do detractors of age verification think are so terrible that it's more important than avoiding, for example, allowing kids first sexual experiences to be pornography. Is that equivalent?Or, what alternative solutions are counter-proposed to avoid these issues without age verification and vpn bans.Note 2 things before responding:1)per the original quote, it is not valid to ignore the trade offs with arguments like "child abuse is an excuse to install civilian control by governments"2) this was not your initiave, another group is the one making huge efforts to intervene and change the status quo, so whatever solution is counterproposed needs to be new, otherwise, as an existing solution, it was therefore ineffective.If any of those is your argument, you are not part of the conversation, you have failed to act as wardens of the internet, and whatever systems you control will be slowly removed from you by authorities and technical professionals that follow the regulations. Whatever crumbs you are left as an admin, will be relegated to increasingly niche crypto communities where you will be pooled with dissidents and criminals of types you will need to either ignore or pretend are ok. You will create a new Tor, a Gab, a Conservapedia, a HackerForums, and you will be hunted by the obvious and inequivocal right side of the law. The notion of right and wrong which is like totally subjective anyways? Or, what alternative solutions are counter-proposed to avoid these issues without age verification and vpn bans.Note 2 things before responding:1)per the original quote, it is not valid to ignore the trade offs with arguments like "child abuse is an excuse to install civilian control by governments"2) this was not your initiave, another group is the one making huge efforts to intervene and change the status quo, so whatever solution is counterproposed needs to be new, otherwise, as an existing solution, it was therefore ineffective.If any of those is your argument, you are not part of the conversation, you have failed to act as wardens of the internet, and whatever systems you control will be slowly removed from you by authorities and technical professionals that follow the regulations. Whatever crumbs you are left as an admin, will be relegated to increasingly niche crypto communities where you will be pooled with dissidents and criminals of types you will need to either ignore or pretend are ok. You will create a new Tor, a Gab, a Conservapedia, a HackerForums, and you will be hunted by the obvious and inequivocal right side of the law. The notion of right and wrong which is like totally subjective anyways? Note 2 things before responding:1)per the original quote, it is not valid to ignore the trade offs with arguments like "child abuse is an excuse to install civilian control by governments"2) this was not your initiave, another group is the one making huge efforts to intervene and change the status quo, so whatever solution is counterproposed needs to be new, otherwise, as an existing solution, it was therefore ineffective.If any of those is your argument, you are not part of the conversation, you have failed to act as wardens of the internet, and whatever systems you control will be slowly removed from you by authorities and technical professionals that follow the regulations. Whatever crumbs you are left as an admin, will be relegated to increasingly niche crypto communities where you will be pooled with dissidents and criminals of types you will need to either ignore or pretend are ok. You will create a new Tor, a Gab, a Conservapedia, a HackerForums, and you will be hunted by the obvious and inequivocal right side of the law. The notion of right and wrong which is like totally subjective anyways? 1)per the original quote, it is not valid to ignore the trade offs with arguments like "child abuse is an excuse to install civilian control by governments"2) this was not your initiave, another group is the one making huge efforts to intervene and change the status quo, so whatever solution is counterproposed needs to be new, otherwise, as an existing solution, it was therefore ineffective.If any of those is your argument, you are not part of the conversation, you have failed to act as wardens of the internet, and whatever systems you control will be slowly removed from you by authorities and technical professionals that follow the regulations. Whatever crumbs you are left as an admin, will be relegated to increasingly niche crypto communities where you will be pooled with dissidents and criminals of types you will need to either ignore or pretend are ok. You will create a new Tor, a Gab, a Conservapedia, a HackerForums, and you will be hunted by the obvious and inequivocal right side of the law. The notion of right and wrong which is like totally subjective anyways? 2) this was not your initiave, another group is the one making huge efforts to intervene and change the status quo, so whatever solution is counterproposed needs to be new, otherwise, as an existing solution, it was therefore ineffective.If any of those is your argument, you are not part of the conversation, you have failed to act as wardens of the internet, and whatever systems you control will be slowly removed from you by authorities and technical professionals that follow the regulations. Whatever crumbs you are left as an admin, will be relegated to increasingly niche crypto communities where you will be pooled with dissidents and criminals of types you will need to either ignore or pretend are ok. You will create a new Tor, a Gab, a Conservapedia, a HackerForums, and you will be hunted by the obvious and inequivocal right side of the law. The notion of right and wrong which is like totally subjective anyways? If any of those is your argument, you are not part of the conversation, you have failed to act as wardens of the internet, and whatever systems you control will be slowly removed from you by authorities and technical professionals that follow the regulations. Whatever crumbs you are left as an admin, will be relegated to increasingly niche crypto communities where you will be pooled with dissidents and criminals of types you will need to either ignore or pretend are ok. You will create a new Tor, a Gab, a Conservapedia, a HackerForums, and you will be hunted by the obvious and inequivocal right side of the law. The notion of right and wrong which is like totally subjective anyways? However this was pretty soft.I was exposed to serious pornography at 10 years by finding a hidden VHS tape in the back of a drawer at a friends house and getting curious. This was hardcore German stuff with explicit violence. This has caused me to have therapy in my lifetime.This was all in the 80s by the way.Therefore anything you are mentioning happened long before the internet, and is totally possible in a completely offline world as well. So how do these new digital laws 'protect children' again? This was hardcore German stuff with explicit violence. This has caused me to have therapy in my lifetime.This was all in the 80s by the way.Therefore anything you are mentioning happened long before the internet, and is totally possible in a completely offline world as well. So how do these new digital laws 'protect children' again? So how do these new digital laws 'protect children' again? Therefore anything you are mentioning happened long before the internet, and is totally possible in a completely offline world as well. So how do these new digital laws 'protect children' again? > And the only way to prove that you checked is to keep the data indefinitely.This is not true and made me immediately stop reading. If a social media app uses a third party vendor to do facial/ID age estimation, the vendor can (and in many cases does) only send an estimated age range back to the caller. Some of the more privacy invasive KYC vendors like Persona persist and optionally pass back entire government IDs, but there are other age verifiers (k-ID, PRIVO, among others) who don't. Regulators are happy with apps using these less invasive ones and making a best effort based on an estimated age, and that doesn't require storing any additional PII. You can do one thing without doing the other. This is not true and made me immediately stop reading. If a social media app uses a third party vendor to do facial/ID age estimation, the vendor can (and in many cases does) only send an estimated age range back to the caller. Some of the more privacy invasive KYC vendors like Persona persist and optionally pass back entire government IDs, but there are other age verifiers (k-ID, PRIVO, among others) who don't. Regulators are happy with apps using these less invasive ones and making a best effort based on an estimated age, and that doesn't require storing any additional PII. You can do one thing without doing the other. I don't think a bulletproof age verification system can be implemented on the server side without serious privacy implications. It would be quite easy to build it on the client side (child mode) but the ones pushing for these systems (usually politicians) don't seem to care about that. Liquor stores, bars, strip clubs, adult bookstores, or similar businesses don't let kids in. The tech industry ignored their social responsibility to keep kids away from adult content. Now, they are facing legal requirements to do so. Tough for them, but they could have been more proactive.

When you purchase through links on our site, we may earn an affiliate commission. Get Tom's Hardware's best news and in-depth reviews, straight to your inbox. Following a rabid weekend of tariff rulings and press conferences, the Trump administration has settled on a blanket 15% tariff for basically all goods entering the United States. This has upended global trade as countries look to confirm their final rates, with many of them having previously negotiated different rates - some higher than 15%, some lower. While Bloomberg suggests China is a big winner of the redrawing of tariff percentages, it also threatens to hand companies like TSMC a big win by negatively impacting U.S. chip companies like Nvidia and Intel. Alongside investing in companies like Intel, the U.S. government has used trade blocks and tariffs to push for companies like TSMC and Micron to open up new manufacturing facilities in America. However, the prevailing sentiment was that with enough investment, tariffs might disappear entirely for a select few. TSMC's announcement earlier this month that it could invest a further $100 billion in advanced manufacturing in Arizona was with the idea of taking advantage of a potential zero-tariff loophole. In late 2025, TSMC accelerated plans to bring its latest manufacturing facilities to the U.S. as a major show of solidarity with the Trump administration's goals. That's all been thrown out the window as of this weekend's Supreme Court ruling and subsequent announcements. But if 15% was what Taiwan had gained for its efforts, and now it faces 15% regardless, it may have been given a golden opportunity. It may be able to leverage existing agreements and investment plans to secure a better-than 15% rate for its products, or it could drop them entirely and still likely only face the same 15% maximum tariff rate as everyone else. And better yet, whichever avenue companies like TSMC go down, they'll have an advantage over American firms doing the same. The vast majority of the world's most advanced semiconductor manufacturing happens in Taiwan, but the Trump administration has made a major play to bring some of that to U.S. shores, even claiming to want as much as 40% of TSMC's total manufacturing to be based in America in the future — something that TSMC has said is impossible. But it has secured massive new manufacturing investments from international firms like TSMC, Micron, and others, as well as investing domestically in Intel. These latest trade tariffs do nothing to help America or American businesses, though. Broad tariffs raising the cost base for everything imported into America means raising prices on those key materials, in turn making U.S.-based chip manufacturing more expensive for everyone involved. Its planned Fabs have potential chip complexity and yield advantages over even some of TSMC's best facilities, though they have yet to start production. Increasing the costs of these raw materials and further squeezing supply chains is not ideal for such a venture. Nothing is clear about these new tariffs, and there's a distinct possibility that they don't apply to semiconductors and electronics, or at least, aren't designed to. But as the Singaporean Ministry of Trade highlights, some products should be excluded from this Section. "In addition, semiconductors and pharmaceuticals are not subject to the Section 122 tariffs, as they may be the subject of Section 232 tariffs that have not yet been imposed." However, as White Case LLP highlighted in January, the Trump administration has already leveraged Section 232 for 25% tariffs on a limited selection of semiconductors imported into America. Those tariffs could easily be expanded with the legal justification that it's for matters of national security. Trump has previously used similar justifications to limit imports of Steel and Aluminum during his first term. The new tariffs are sweeping, confusing, and very temporary, at least for now. It throws into question all existing deals, which were less foundationally secure than traditional trade agreements anyway. In the near term, though, it's looking like some of the greatest beneficiaries of America's further turn inwards towards self-sufficiency may be helping anyone and everyone but America itself. Jon Martindale is a contributing writer for Tom's Hardware. Tom's Hardware is part of Future US Inc, an international media group and leading digital publisher.

When you purchase through links on our site, we may earn an affiliate commission. The Asus ROG Swift PG32UCDM3 has no real flaws, it is a superlative gaming monitor with speedy play and a gorgeous picture to match. It's expensive but if you have the budget, there's nothing better among 32-inch 4K panels. Super quick with smooth motion and instant response Our expert reviewers spend hours testing and comparing products and services so you can choose the best for you. Flagship gaming monitors come in many shapes and sizes, so focusing on one category is impractical. On my planet, flagship means OLED, and this world's newest resident is Asus' ROG Swift PG32UCDM3. It's a 32-inch Quantum Dot OLED with 4K resolution, 240 Hz, Adaptive-Sync, ELMB, and wide gamut color. HDR carries a VESA DisplayHDR 500 certification, and in addition to HDR10 support, you get Dolby Vision too. Asus has added a technology called BlackShield that makes the screen's front surface harder and improves perceived black levels. To that end, it operates only up to 120 Hz and is effective at reducing motion blur at low frame rates. If you have the latest GeForce 50-series or Radeon RX 7000, the PG32UCDM3 has a DisplayPort 2.1a input that supports a full 80Gbps bandwidth. It's backward compatible with DP 1.4 and includes Display Stream Compression (DSC). Two HDMI 2.1 inputs also support 3840x2160 at 240 Hz, as does the single USB-C input. Full calibration controls are provided, though my sample proved nearly perfect out of the box. The other screen layer of interest here is called BlackShield. It adds scratch protection with a higher hardness rating and better manages ambient light, which makes blacks deeper. While any OLED can do this in a dark room, most have a reflective screen that shows bright sources like lamps or sunny windows. Video processing is top-shelf, with G-Sync and FreeSync support across all inputs at 240 Hz. You also get ELMB, which is rare in the OLED genre. Get Tom's Hardware's best news and in-depth reviews, straight to your inbox. Asus provides its large suite of OLED care options, including logo and perimeter detection, pixel orbiting, and a refresh routine with reminders. A proximity sensor can blank the screen when you leave your desk. Also included is the full array of GamePlus options, including aiming points, sniper modes, timers, a stopwatch, and multiple frame counters. And you get GameVisual with its nine picture modes. Peripheral features include LED lighting, USB ports, programmable function keys, and Asus' DisplayWidget desktop app, which lets you control the PG32UCDM3 from a PC or Mac desktop. The only thing missing are internal speakers, but you do get a 3.5mm headphone jack. The PG32UCDM3 carries a flagship-appropriate price of $1,299 at this writing. That isn't low but it is better than what a monitor like this would have cost just a few years ago. For that sum, you're getting a monitor with every available gameplay and image-enhancing technology that is suited for any task, be it work or entertainment. The ROG pouch is bursting with cables, including IEC power, DisplayPort, HDMI, and two USBs. If you'd rather use a mounting arm, an adapter bracket with 100mm VESA lugs is also in the box. This helps with cooling, which is entirely passive; there are no fans in evidence. The lens is attached with magnets, so it's easy to make a change. All these bits can be controlled from the OSD or turned off if you like. The front bezel is flush and thin, measuring 8 to 14 millimeters wide. With such a large screen and bright image, you barely notice the frame. A small ROG logo, backlit, of course, protrudes from underneath and indicates where the two buttons and the OSD joystick are. Alternatively, you can use Asus' DisplayWidget Center on the Windows or Mac desktop. The upright swivels on it, just 15 degrees to either side. You also get 5/20 degrees tilt and a 3.3-inch height adjustment. For video, you get a DisplayPort 2.1a (UHBR20, 80 Gbps), two HDMI 2.1 (up to 3840x2160 @ 240 Hz), and a USB-C port that mimics DP functions and provides 90 W of power. USB 3.2 is supported with one upstream and two downstream ports. For audio, you get a 3.5mm headphone jack; there are no internal speakers. Gaming is up first with an Adaptive-Sync toggle, ELMB, GamePlus play aids, GameVisual picture modes and Shadow Boost, which is used to enhance dark area visibility. GamePlus includes aiming points, sniper modes, timers, a stopwatch and display alignment marks. GameVisual has nine picture modes with Racing as the default. If you want sRGB, I recommend selecting that option from the Display Color Space menu rather than using the sRGB Cal Mode. Using the full gamut for SDR delivers almost 108% coverage of DCI-P3. In the Image menu is a new option I haven't seen before, HDR Format. It's found in games like Halo Infinite, Call of Duty: Modern Warfare II, and Microsoft Flight Simulator. If a display can't hit 1,000 nits, it has to tone map, basically guess what the intended levels are. The PG32UCDM3 offers four HDR10 modes, which can be adjusted for brightness and contrast if you like. Console HDR includes a toggle called Dynamic Brightness Boost, which does just what it says: it increases peak highlights to provide more impact. You can also tweak each color individually for saturation. OLED Care has many options to prevent burn-in like a screen saver, pixel refresh, pixel orbiter and detection of static logos and perimeter elements. The PG32UCDM3 has full PIP and PBP options for those who want to view two video sources at once. It can play in any color with multiple effects, or static if you prefer. The four joystick directionals can be programmed to quick access functions like GameVisual, GamePlus, input selection and more. This ensures backwards compatibility with older graphics boards. The PG32UCDM3 looks and measures well in its Racing picture mode. Calibration is not required, but some small gains are possible by dialing in the RGB sliders in the color temp menu. Gamma tracks on the reference, so no change is needed there. And color conforms to DCI-P3, sRGB or wide gamut, which covers over 107% of DCI-P3. When it's off, the SDR peak is just over 500 nits from a 25% window pattern. For HDR10, you get four modes and Dolby Vision has three of its own. While there are more immersive gaming monitors like big curved ultra-wides, there are none more useful for a wide variety of tasks than a 32-inch 16:9 flat panel like the PG32UCDM3. There is nothing it cannot do well. With almost 108% DCI-P3 coverage, it is among the very best. There was no hurry to calibrate, and in fact, I didn't touch anything except the brightness until the testing phase began. I enjoyed lots of fragging before getting down to work. Though my gaming skills are average at best, I benefit from a high-performance screen when playing. DisplayPort 1.4 with DSC provided enough bandwidth to prevent any hesitation in movement. I tried out ELMB at 120 Hz and found it completely usable. Users with older video cards will be able to enjoy this monitor at 120fps with the same smoothness I saw at 240. As for the effect of BlackShield, I had to turn on a few room lights to see its benefit. If you play in a dark or dim space, the PG32UCDM3 looks like every other premium OLED. I won't be surprised to see this tech appear elsewhere. To check out the Dolby Vision support, I hooked up a Panasonic DP-UB9000 4K Blu-ray player and watched the demo material on Spears and Munsil 4K Benchmark suite. This allowed me to watch the same clips in HDR10 and DV. Dolby Vision had more thoroughly rendered highlights which not only exposed more image detail, but it also increased the perception of contrast. Color was equally rich between the two formats, but the extra punch in Dolby Vision's highlights was easy to see. My reference screen is a 32-inch UHD OLED, so the Asus made me feel right at home. Windows looks best to my eyes at a font scale value of 150%. That works well with the monitor's 140ppi pixel density. You can see the dots at around eight inches away, but farther than that, and you won't see any jaggies. No edge enhancement or other sharpening aids were required here. I appreciated the PG32UCDM3's variable brightness feature and the fact that it would remember each brightness setting, so I only had to adjust it once. That way, the peak is equalized between modes. Turning Uniform Brightness off makes video and games look a little more impactful, while turning it on is better for productivity. This is a nit-pick on my part, but I feel that every monitor should have some kind of audio besides the headphone jack, even if it's just for system sounds. I can think of no better choice for a high-end PC or Mac if you need the best possible do-it-all display. Christian Eberle is a Contributing Editor for Tom's Hardware US. He's a veteran reviewer of A/V equipment, specializing in monitors. Christian began his obsession with tech when he built his first PC in 1991, a 286 running DOS 3.0 at a blazing 12MHz. In 2006, he undertook training from the Imaging Science Foundation in video calibration and testing and thus started a passion for precise imaging that persists to this day. He enjoys watching movies and listening to high-end audio in his custom-built home theater and can be seen riding trails near his home on a race-ready ICE VTX recumbent trike. Christian enjoys the endless summer in Florida where he lives with his wife and Chihuahua and plays with orchestras around the state. Tom's Hardware is part of Future US Inc, an international media group and leading digital publisher. © Future US, Inc. Full 7th Floor, 130 West 42nd Street, New York,

Save up to $680 on your pass with Super Early Bird rates. Defense Secretary Pete Hegseth is calling in Anthropic CEO Dario Amodei to the Pentagon on Tuesday morning to discuss the military use of Claude, according to reporting from Axios. Anthropic signed a $200 million contract with DOD last summer, and Claude was reportedly used during the January 3 special operations raid that resulted in the capture of Venezuelan president Nicolás Maduro, an episode that brought the two sides' tensions into the open. A source told Axios that Hegseth is giving Amodei an ultimatum: play ball or be banished. It's unclear whether he's bluffing — replacing Anthropic would be a significant undertaking. But the stakes are real: A supply chain risk designation would void Anthropic's contract and force other Pentagon partners to drop Claude entirely. Save up to $680 on your pass before February 27.Meet investors. Hear from 250+ tech leaders, dive into 200+ sessions, and explore 300+ startups building what's next. Every weekday and Sunday, you can get the best of TechCrunch's coverage. TechCrunch Mobility is your destination for transportation news and insight. Startups are the core of TechCrunch, so get our best coverage delivered weekly. Provides movers and shakers with the info they need to start their day. By submitting your email, you agree to our Terms and Privacy Notice.

This makes it more expensive than some brand-new cars. When you purchase through links on our site, we may earn an affiliate commission. Get Tom's Hardware's best news and in-depth reviews, straight to your inbox. MSI's limited-edition RTX 5090 Lightning Z launched to great acclaim at CES 2026, with the ultra-powerful GPU breaking overclocking records even before it launched. Its earth-shattering capabilities are only matched by its wallet-shattering $5,090 asking price — but scalpers are seemingly ready and willing to shell out that amount in the hopes of getting an even bigger payday when stock has run out. We're unsure if this is a legitimate offer, though, as the seller's profile mostly showed cheaper replacement Ikea parts and a few electronics, mostly priced under US$100. When we checked sold listings for sealed, brand new MSI RTX 5090 Lightning Z GPUs, the price ranged from around $6,700 to a little over $8,800. This is a bit more reasonable, but still at least $1,500 over MSI's price and more than three times the $2,000 MSRP Nvidia set for the RTX 5090 Founders Edition. Nevertheless, gamers and enthusiasts bent on breaking records will likely pull the trigger on this purchase just for the extra fps that it delivers. Aside from that, MSI also released a 2,500-watt XOC BIOS exclusively to overclockers to get every bit of GPU performance from the expensive GPU. One overclocker tried to achieve a world record using this BIOS, but they apparently had an earlier version of it, resulting in a crack from the thermal shock delivered by the massive amounts of power. Thankfully, they still have four more samples of this extreme GPU, allowing them to continue working on it and achieve higher benchmark results in the future. Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds. Get Tom's Hardware's best news and in-depth reviews, straight to your inbox. Jowi Morales is a tech enthusiast with years of experience working in the industry. Tom's Hardware is part of Future US Inc, an international media group and leading digital publisher.

All products featured here are independently selected by our editors and writers. If you buy something through links on our site, Gizmodo may earn an affiliate commission. No matter what the gadget skeptics say, there is still room for innovation in PC peripherals. Logitech's $180 G Pro X2 Superstrike is here to upset the status quo. Instead of the traditional mechanical or optical mouse click switches, the G Pro X2 Superstrike uses magnetic fields to register when you hit either of its mouse buttons to a specified depth. Modern high-end video game controllers use of Hall effect thumbsticks and triggers, which makes them more durable than older, physical sticks and switches. This same technology is found inside the G Pro X2 Superstrike, which means this mouse is—supposedly—more durable and far more customizable. And even if that sounds like a lot of extra work, Logitech's G Hub app makes it relatively simple to set your preferred click for the type of games you play. The G Pro X2 Superstrike feels like no other mouse I have ever used. Instead of a “click,” each press of the left mouse button feels and sounds like a “thwomp.” It's more subtle than any other mouse with an optical switch, and that may make it more appealing. With its baseline 8,000Hz polling rate in wireless mode and an adjustable DPI (dots per inch, which measures how fast your mouse can be) between 100 and 44,000, it already hits the bar it needs to for esports-level gaming. See Logitech G Pro X2 Superstrike at Best Buy When you can manually set the depth to register an input, that means you can trigger the input at a rapid pace. The G Pro X2 Superstrike sports an optional “Rapid Trigger,” enabling ultra-fast clicks. Whether he's telling the truth or not, the rapid-click capability has allowed one player to reportedly set a record for most mouse clicks in a minute. Yiğit “Yigox” Arslan managed to click 760 times in a minute, or around 12 clicks per second, which the Guinness Book of World Records effectively confirmed in a comment on a LinkedIn Post. Does that ultra-fast click enhance your ability to better match skilled opponents in games like Valorant or Counter-Strike 2? With the right kind of haptic feedback, DPI , and rapid-click tuned to my liking, I found that I was able to snap off single shots at a rapid pace with my AK in Counter-Strike. I was actually aiding my team even though I'm not nearly as good at clicking on heads as some other kings of Counter-Strike 2. You can assign various commands and macros to each of the five buttons and set your preferred DPI. That's all well and good, but the real nugget of customization is found under the “HITS” tab inside G Hub. HITS stands for “Haptic Inductive Trigger System,” though all you need to know is that you can set the actuation point for left and right mouse buttons and change the mouse's haptic settings. I found my sweet spot was setting the haptics almost as high as they could go with a slightly more shallow than default actuation. Even then, I didn't find I was generating any accidental inputs even with my finger lying on the proverbial trigger. What's interesting about this haptic mouse click is how it will remain working even with the 2.4GHz “Hero 2” dongle unplugged. Back in 1999, Razer's original Boomslang mouse (not the $1,337 Boomslang revival) caused controversy for its higher-than-normal DPI at gaming tournaments, at least according to Razer. Now, high DPI and polling rates are well-established standards. Just because you have a unique mouse doesn't mean you'll be better than everybody else who is also trying to line up headshots. Not only was it just the right scale and ergonomics for my hand, but its latest-gen optical switches and low-latency connectivity gave it the slightest edge compared to other similarly weighted PC controls. Going several rounds in a variety of FPS and RTS games, I could tell that the G Pro X2 Superstrike was modifying my gameplay to a surprising degree, though more so in a twitch-based shooter like Counter-Strike 2. Playing Hades II with a mouse and keyboard isn't my forte, but I preferred the rapid spam of button presses I could achieve with the G Pro X2 Superstrike compared to other mice. I went as far as to conduct multiple rounds of tests comparing my click rate between Razer's and Logitech's top-end gaming mice. With the DeathAdder V4 Pro and its newfangled optical click sensors, my top score was 179 clicks in 30 seconds and a 5.97 clicks per second ratio. With the G Pro X2 Superstrike set to the fastest click settings possible, I managed to top off at 188 clicks per second in the same time and a 6.27 clicks per second ratio. Such a marginal difference won't actually change my gameplay. When rapidly clicking on an optical sensor like Razer's, my finger tends to seize up, leading to the occasional misclick. Either way, I'll never be as good as Yigox (and I don't actually want to be). The similarly priced DeathAdder V4 Pro still has an advantage with connectivity. It will also notify you of when your mouse's battery runs low. Logitech's G Pro X2 Superstrike is only slightly easier to transport. For the $180 you spend on the Pro X2 Superstrike, you're essentially buying a Logitech Pro X Superlight 2 with a unique click sensor and few other standout hardware features. Its size and shape don't offer my preferred form of ergonomics. I just wish it didn't look so goofy. A HyperX Pulsefire Haste 2 Mini clocks in at 59g. I know there are esports pros who will swear they can feel the difference, but most users couldn't possibly measure grams of weight in their palm, like they were some gamer-fueled rendition of “The Princess and the Pea” fable. I would have preferred if the mouse were less symmetrical. Lefties will have a better time with this mouse than others, though they still won't have access to the two side buttons unless they claw their hand further back onto the mouse hump. Some more particular gamers may demand something even floatier. What I can't forgive is the overall look of this mouse. It's not as if I'll be paying much attention to mouse aesthetics when in-game. Then again, merely leaving it on my desk in between rounds of Counter-Strike would have me wishing I could stuff it away behind a curtain in case anybody comes too close to judge. Logitech claims the gaming mouse can get 90 hours of active playtime before you need to plug it in. That number will likely vary based on what haptic and DPI settings you choose. I personally find specs like this negligible unless you plan to take these mice on the road and there's no single plug or USB-C cable in sight. There is a meaningful advantage you can get from gaming-specific hardware. However, it's less about having an upper hand than it is about raising the ceiling for your own capabilities. I can play a fast-paced first-person shooter at 60 fps and play just about as well as I would at 120 fps or even twice that. That 240Hz monitor on my desk doesn't naturally grant me some preternatural ability to achieve good positioning in Overwatch. A gaming headset like the Razer Blackshark V3 Pro, whose drivers and equalization (EQ) settings are tuned for hearing other players' footsteps and gunshots, will naturally enable better play. It doesn't change your skill level and the same can be said about the Logitech G Pro X2 Superstrike. If it modifies how you play, it will be to a minimal degree compared to most other high-end gaming mice available. However, it is the kind of mouse that's worth getting used to. I can already tell this design will become the next big thing that every other company will eventually copy. Somebody will eventually need to come along and change mice before they get stale once more. Until then, I'm happy with the slick—gaudy-looking—G Pro X2 Superstrike on my desk. See Logitech G Pro X2 Superstrike at Best Buy Subscribe and interact with our community, get up to date with our customised Newsletters and much more. It surprised me, but Fender's first pair of wireless headphones has some solid features that are actually worth paying for. A new State of Gaming analysis reveals Chinese success in an otherwise suffering industry. The company behind Lite Brite said it wants to make Arcade1Up feel even more authentic than before. We may not have to wait on Apple anymore.

Or at least they're not eating the internet. The people who build and maintain the nearly 600 subsea cables that carry almost all of our intercontinental traffic—supporting just about every swipe, tap, Zoom, and doomscroll anywhere on the planet—have a love-hate relationship with this myth, which has persisted for decades. They might even hate that I'm starting this piece with it. Rolling out this week, WIRED's journalistic commissions on technological decommissions—from broken-down electric cars to falling-down space stations. Sometimes they'll lunge for a cable that's being pulled out of the water. Rats can be a threat on land, because their incisors never stop growing, so they like to file them down on semisoft cables. But nobody ever asks about rats, maybe because, as a friend of mine pointed out, “sharks make you cool, but rats sound like you have a problem.” Sometimes people ask about satellites or, especially in Sweden (where I live), about alleged sabotage in the Baltic Sea. But historically, shark bites have commanded the most attention. That's the real story of subsea cables—not sabotage or sharks, but the humans who take care of the physical stuff that keeps all of our digital communication flowing. Most people don't even think about how quickly we've accepted instantaneous communication as normal, even those of us who can remember when an international phone call had to be booked in advance. The more people I meet in this industry, in this network of networks of people and things, the more insulting it sounds to hear that “we” only notice it when it breaks. (Who is this “we,” I always want to know?) I also need to clear up something else. Most people call them “internet cables,” but technically, fiber-optic transmission was developed for telephone calls. One of the people involved was an English scientist named Alec Reeves, who also spent his time working on psychokinesis and telepathy. With fiber, voices become light, pulsate across spiderweb-thin strings of glass, and become voices again in your handset on the other end. Maybe there isn't that much of a conceptual leap between that and moving things with your mind. TAT is short for Trans-Atlantic Telephone, and TAT-8—built by AT&T, British Telecom, and France Telecom—was the eighth transoceanic system across the Atlantic. It was the first to use optical fibers to transmit traffic between Europe and the United States. When TAT-8 went into service on December 14, 1988, the science fiction writer Isaac Asimov spoke on video link from New York to audiences in Paris and London: “Welcome everyone to this historic transatlantic crossing,” he said, “this maiden voyage across the sea on a beam of light.” AT&T made a TV ad, in which an earnest voice-over promised a “worldwide intelligent network” where people could send information in any format to anyone they want. You have a call booked for Poland?” “I have your call to Russia.” “What city in Cuba are you calling?” If they were looking to inspire viewers, it wasn't with the promise of the internet, which was still too niche for most of us to comprehend, but with the end of the Cold War. Rather than being the last cable ever needed, as had originally been believed, it was full to capacity within 18 months, by which point there were other cables, like PTAT-1 across the Atlantic and TPC-3 in the Pacific. By 2001, the TAT series was up to number 14. After developing a fault that was too expensive to be worth fixing, TAT-8 was taken out of service in 2002. It's been sitting on the seabed until now. The MV Maasvliet docks in Portugal to offload recovered fiber-optic cable. TAT-8 is currently being pulled up and sent for recycling by Subsea Environmental Services, one of only three companies in the world that's made cable recovery and recycling its entire business. Cable companies sometimes recover their own cables after they take them out of service, and some retired cables get new life in scientific research or military use, but most of them—most of the 2 million kilometers of it all—are still right where their former owners left them. The seabed is a lot busier than you might think, so these operations are clearing space for new cables, along routes that are proven and efficient, rather than disturbing new sections of the sea floor. It's after midnight on a cool August night, and my friend Fiona Marron—here to take photos and videos—and I are watching Subsea's brand-new diesel-electric cable recovery vessel, the MV Maasvliet, dock in the Portuguese port of Leixões, just outside of Porto. The 14 people on board are two weeks overdue because hurricane season arrived early, and they had to dodge storms Dexter and Erin, which meant they collected more stress and less cable than expected. During the next week or so, they'll offload 1,012 kilometers of TAT-8, resupply the ship, then set out again to pick up another load. They drop the gangway, and there are hugs between the crew and Peter Appleby, operations manager from Subsea. Up on the bridge, we meet Captain Alex Ivanov, who has been at sea for 30 years and still takes pictures of sunsets. He scrolls through his phone to show Peter a blazing red and orange sky, then photos of some of the dorado he caught, because when cable ship people aren't fishing for cable, some of them go fishing for fish. Alex helped design it, and this is only its fourth trip out since it left drydock in January 2025. Then he zips off, getting ready for tomorrow, when he'll hand charge of the ship over to another captain, Vlad. Vlad will show up wearing a new T-shirt that says “Everything can go wrong at sea” on the front and “Not on my fucking watch!” on the back. The ship's fridge is restocked at port. Fiona and I are also the first strangers any of these people have seen in two and a half months. I'm here in Leixões because I'm a researcher in the material culture of the subsea cable industry, and I consider it my business to help people understand that the networks we rely on are made of physical things, created and maintained by people, so that we can stop saying infrastructure is invisible as if the people are invisible too. Satellites are still an important component for resilient physical infrastructure, especially in areas with few or no fiber connections, but they haven't been able to compete on capacity since the 1990s. Back in the 1970s, though, satellite technology seemed so promising that the Federal Communications Commission made it clear to AT&T: If you don't do something revolutionary with cables, we're not going to grant permission for any more intercontinental submarine connections. At the time, cables relied on copper, and there's only so much capacity you can cram into a bundle of wires. So, in 1978, Bell Labs, along with its British counterpart, STC, committed to installing a nearly 6,000-kilometer-long submarine fiber connection between the US, UK, and France. In Holmdel, New Jersey, Bell Labs began testing out cables, and in 1985 the company deployed its first live test system, known as Optican-1, between two of the Canary Islands. Optican-1 worked, but it had a series of what are called shunt faults, where damage to the insulation interrupts the electrical signals. “I'm supposed to be giving this huge talk, that there's this wonderful technology and it's working fine, and it's going into service, but we had this big question mark,” she recalls. They didn't know what had caused the faults. Jack Sipress, who in Stafford's recollection was two levels above her at Bell Labs, got on the bus to the conference center. “And he says, ‘I have the shark teeth,'” Stafford tells me. So we went to the conference and announced to the world that it was shark teeth.” AT&T even included four pages about shark-bite mitigation in its 36-page press kit for TAT-8. Sipress wasn't lying about the teeth, but it's hard to know what really happened. Stewart Ash, who was part of the UK team at STC, insists that most shark claims really are false. If the Optican-1 was installed with too little slack, though, and hung above the seafloor in some areas, a shark might've munched down. “While we at STC didn't believe it,” he says, “we were swept up in the frustration or fear that sharks could interrupt these very important, brand-new cables.” To be absolutely sure, AT&T funded research at two aquariums: in Mystic, Connecticut, and Sarasota, Florida, where researchers let some dogfish and lemon sharks get a little hungry and then tested to see if they bit any of several different cables that were emitting electrical fields in different patterns. They didn't, except in seemingly random cases. (To be certain about this myself, I took my shark-obsessed 5-year-old to a local aquarium, where we spent 15 minutes trying to figure out how a friendly 3-foot dogfish, whose mouth looks like the coin slot of an old payphone, could do more than give a cable a soft boop.) Experts also went out into the ocean and pulled different species of sharks onto the deck to force-feed them sections of cable. They sent shark teeth to the NYU School of Dentistry, to have molds made and mounted onto shark jaw simulators, which then chomped on sections of cable. The result was that lightweight deep-sea fiber was produced, from the start, with what they called “fish bite protection,” which helps against abrasions and other types of everyday damage that can happen in the sea. Turns out, we owe sharks a thank-you, and probably an apology for the force-feeding. A long-haul submarine telecommunications cable needs repeaters to boost the optical signal to cross the distance, and TAT-8 had more than 100 of them, each encased in a watertight, pressure-tested housing that could survive up to 8,000 meters down. In a pile, they look like a dead kraken, ready for one last writhe on the dewy deck. Human hands painted the casings before they went into the water 38 years ago, and it's humans who pull them out, also with their hands. He loves the teamwork and wouldn't dream of going onto a cargo ship—too much waiting around. You grasp it, and as the ship tosses, you walk backward in slow circles to coil the cable in a neat stack, because fiber cable has to be coiled by hand. Another coiler describes the shifts as 14 cigarettes long. Eight hours divided into half-hour blocks so you don't get too woozy: 30 minutes on, 30 minutes off, up the ladder for two cigarettes. Peter, the operations manager, hands two pairs of utility gloves to Fiona and me. Do we want to go into the hold? It's 10 meters down a vertical ladder, but I didn't travel here to just stand at the top of a ladder and shout “What's it like down there?” Fiber-optic cables tend to be skinnier than people expect. The ship's hold has five cable tanks, each about half full. Most people are surprised when they see how small a submarine telecommunications cable is, but even those are usually the black and yellow steel-armored portions used in shallow water. This cable, from the deep-sea sections, is the diameter of a taper candle, and it looks like giant cooked spaghetti. I try to imagine being in here when it's 30 degrees Celsius, the ship tossing up and down, and trying to walk in slow, backward circles. He turns down the music—a mix of Ukrainian techno, American classic rock, and a medium dose of death metal—to tell me about what everyone here seems to agree is the most exciting part of cable recovery: catching the cable. They have a route positioning list, a spreadsheet that shows the precise coordinates of every joint, splice, and repair—along with who did it. To take the cable off the seabed, all you get is a hook, a rope, those coordinates, and your senses. “When we get to the position, we slow down to keep it from flying or dancing.” Everything Stephen tells me sounds like trying to fly a kite in space, except this is all done on the deck of a ship, with ocean swells sometimes over 3 meters—if the swells hit 4, it's too harsh to work. Once the hook is in place, you have one job: Keep your eye on the line, watch for a bite. Captain Alex has been working with Subsea since its early days. Cables weren't laid to be picked up again. The cable can shift from its initial position or be blocked by gravel or sand.” They're still figuring it all out. As Subsea cofounder John Theodoracopulos puts it: “I liken a lot of what we do to cleaning up space junk or all the oxygen bottles that are left at base camp at Everest.” Now that I've seen all the planning and experience that goes into an operation to find and recover a cable, it's even harder to take seriously the idea that enemy saboteurs are regularly pulling this off. A more legitimate concern is disturbing the seabed, but researchers at the UK's National Oceanography Center have started looking into the environmental impact of decommissioning, and it's not as much as you might think. Very few cables in service today cross sensitive ocean habitats. Where that's the case, they leave those segments in place. They also only recover cable that's sitting on the surface of the seabed, and they know exactly where it all is because of that spreadsheet. Cables don't even tend to attract sea life colonization very often. The “reef effect” makes a cool story, but it seems that, just like sharks, most sea life is just not that into cables. Captains Vlad and Alex aboard the Maasvliet. Departing crew members are starting to say their goodbyes. Captain Vlad is passing out nuts and chocolate; Alex will do the formal handover later today. Chief engineer Sergei is just about done with the maintenance work needed to hand over to the next chief engineer, also named Sergei. “This coffee machine is my wife!” he shouts. In a few days, the cable tanks will be empty. The bales will be loaded “breakbulk,” as it's called—directly into the hold, the way it was done before containerization—and brought to South Africa, to Mertech Marine, which also specializes in cable recovery, which Theodoracopulos tells me is a “collegial competitor.” Mertech is the only cable salvage company with a recycling facility of its own. It will break the cables down: steel, copper, two kinds of polyethylene. The fiber itself is just about the only part of the cable that doesn't make sense to recycle, but there's lots of steel, and that will become things like game and vineyard fencing. Polyethylene is one of the easiest plastics to recycle, and that will be sent to a facility in the Netherlands, where it will be turned into pellets that can be used for non-food-grade plastics. It spent close to a decade as the largest empty office building in America and is now a mixed-use complex called Bell Works, although it's probably most recognizable as the headquarters of Lumon Enterprises in the Apple TV show Severance. The current owners found 18 kilometers of subsea fiber from an early sea trial for TAT-8 in the basement, and they commissioned an architecture firm to come up with ideas for what to do with it, among them a giant slinky. No one has used the old Ocean Simulation Lab for a production set, but you can also rent that—on a production location website, you'll find it labeled a “mad scientist's lair.” Some of the TAT-8 people are still around because there are two things that keep people in the subsea business: They like people, and they love messy problems. And the shark research makes a lot more sense—they had a big bet, a blank check, and an almost heroic sense of pride in their work that drove them to go down even vanishingly small rabbit holes. I suppose there's a third reason a lot of the people are still around: Most people in this tiny industry are Generation X or older, and sometimes they cart around so much institutional knowledge that they can't retire. Stafford is near retirement age, and the guy who introduced me to her, Jean Devos, got his start making telegraph cables in the north of France in 1961 and still works as an adviser. The first thing Stafford said to me on Zoom was, “How is he? Does he look well?” The subsea world has been trying to recruit and train younger talent for at least the past decade, so the industry vets can get their rest. Now it's my turn to leave, so I'm climbing around the ship, saying my goodbyes, having a few last chats in the smoking area outside the crew quarters—where everyone is when they aren't working. The Subsea guys also gave me a branded baseball cap, which has a stylized cross-section of submarine cable on it. Except, how many people know what subsea cables look like? And you can't wear a hat through security, so it goes into the bucket. Alternatively, you can submit a letter to the editor at mail@wired.com. A wave of unexplained bot traffic is sweeping the web Big Story: The women training for pregnancy like it's a marathon Listen: Silicon Valley tech workers are trying to stop ICE WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast.