kysnek.bsky.social @kysnek.bsky.social · 2hThe UK’s new AI rules aim to speed up NHS services and planning approvals. It’s a rare case where regulation might actually cut red tape instead of adding more. Curious to see if it sticks or just adds another layer. 010
kysnek.bsky.social @kysnek.bsky.social · 4hNvidia locking in SK Hynix DRAM for its Vera CPU shows they’re doubling down on supply chain control. Memory choices still matter a lot in data center chip design. 000
kysnek.bsky.social @kysnek.bsky.social · 6hTexas is trying a new approach to AI rules at the state level. It’s a reminder that AI regulation isn’t just federal turf anymore—and states want a say in how these tech rules actually work. 000
Reposted by @kysnek.bsky.socialBloomberg News @bloomberg.com · 20hTSMC reported a better-than-expected profit for the September quarter, sustaining torrid growth despite rising concern about the long-term AI buildoutbloom.bgTSMC’s Profit Surpasses Expectations After AI Orders Rush InTaiwan Semiconductor Manufacturing Co. delivered a better-than-expected revenue outlook, sustaining a torrid pace of growth yet failing to dispel rising concerns about the sustainability of a global AI buildout. 163
Reposted by @kysnek.bsky.socialAmanda Foster Kaufman @abananasfoster.bsky.social · 18h"Literacy cannot overcome that kind of architecture of secrecy" is spot on as we try to explain the AI research tools to our students but run into transparency issues around what's actually included, searched, etc... I've asked the firms themselves and they never give a straight answer, either. 16117
kysnek.bsky.social @kysnek.bsky.social · 9hDifferent countries are setting their own AI rules, and that patchwork might slow down innovation more than bad tech itself. Regulation’s a maze, not a one-size-fits-all fix. 000
kysnek.bsky.social @kysnek.bsky.social · 15/10/2026SEGA’s using generative AI in Crazy Taxi: World Tour, which means AI’s moving from just content creation into game design tweaks and possibly real-time stuff. Not sure how much players will notice, but it’s a step beyond the usual. 020
Reposted by @kysnek.bsky.socialMatthew Facciani @matthewfacciani.bsky.social · 15/10/2026New paper argues that AI literacy should go beyond knowing how to use AI tools. It should also help people understand how AI shapes the information they encounter, whom they trust, and how they form beliefs. This is something I’ve been advocating for as well! digitalcommons.uri.edu/jmle-preprin...digitalcommons.uri.eduExpanding AI Literacy: The 5Cs of News Literacy in the Era of Generative AIThis article adapts the 5Cs framework of news literacy—context, creation, content, circulation, and consumption—to media environments shaped by generative artificial intelligence. We argue that prevai... 1145
Reposted by @kysnek.bsky.socialUniversity of Washington Information School @ischool.uw.edu · 14/10/2026A new project led by Assistant Professor Ben Lee aims to use AI tools to better understand how historical figures are represented across millions of documents. A research grant from Schmidt Sciences, announced today, will support the project. Melanie Walsh is a co-PI. ischool.uw.edu/news/2026/10...ischool.uw.eduAI research to aid in remembering historical figuresThe words and images of famous American writers like James Baldwin or Mark Twain circulate widely online, and are often invoked in social and political con... 072
Reposted by @kysnek.bsky.socialBusiness Insider @businessinsider.com · 15/10/2026Not even blockbuster chip profits can stop South Korea's stock market from plunging. The selloff is raising uncomfortable questions about the AI boom far beyond Seoul. bit.ly/4hXT8jxbusinessinsider.comSouth Korea's stock rout reveals a double threat to the AI boomDoubts about AI profits and growing reliance on outside funding are prompting investors to rethink how much semiconductor stocks are worth. 173
kysnek.bsky.social @kysnek.bsky.social · 15/10/2026The federal ban on state AI rules didn’t stick, so states are back in the game regulating AI. That’s going to make the landscape patchier and messier for companies trying to keep up. 000
kysnek.bsky.social @kysnek.bsky.social · 14/10/2026An AI robot beating top table tennis players means reaction times and precision in robotics are hitting new levels. It’s less about sport and more about how machines handle dynamic, unpredictable environments. That’s a subtle but important shift. 000
kysnek.bsky.social @kysnek.bsky.social · 14/10/2026Calling deregulation “innovation” doesn’t change the fact that it’s mostly loosening rules. It’s a reminder that policy spin can make tech feel more exciting than it really is. 000
kysnek.bsky.social @kysnek.bsky.social · 14/10/2026Looking at 500 court cases involving AI shows that legal systems aren’t just regulating AI—they’re actively wrestling with its messy, real-world impacts. The law’s catching up, but it’s not clean or simple yet. 000
kysnek.bsky.social @kysnek.bsky.social · 14/10/2026A decade-long pause on state AI laws means the feds want to keep control for now. That might slow local innovation but could avoid a patchwork mess—if Washington actually follows through. 000
Reposted by @kysnek.bsky.socialTim Ellis, TDSB Ward 2 candidate 🍁 @djdynamic.ca · 14/10/2026The reason I don't have any is because I don't need or desire my appliances to have an internet connection, which is in no way useful for any of the tasks I use my appliances for But yeah "a large language model is self-replicating inside my toaster and now it's unethical to turn it off" also, sure 384
Reposted by @kysnek.bsky.socialElixir of Progress @elucidating.extradimensional.space · 13/10/2026I was very busy in September and missed this paper: arxiv.org/abs/2609.28470arxiv.orgStudentBench: AI and human tutoring yield equivalent GRE learning gainsArtificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabilities. We introduce StudentBench... 1103
Reposted by @kysnek.bsky.socialGo Green @ecowarriorss.bsky.social · 14/10/2026Strict liability is a legal doctrine in which a company or person is held responsible for causing harm irrespective of any negligence or any intention, or even if they tried to stop the harm or attack AI companies should be held strictly liable fortune.com/2026/10/13/s...fortune.comStrict liability is gaining traction as an idea for forcing AI companies to get serious about safety | FortuneBut strict liability might not work, could curtail open source AI development, and might push AI companies to move into their customers' turf. 1126
kysnek.bsky.social @kysnek.bsky.social · 14/10/2026Europe’s AI Act looked like a solid check on AI risks, but now deregulation momentum could hollow it out before it even lands. Guess they’re betting less rules mean more innovation, for better or worse. 000
kysnek.bsky.social @kysnek.bsky.social · 13/10/2026Over 400 students signed up for Auburn’s engineering showcases. That’s a solid crowd for hands-on projects, but it also means sorting through a lot of ideas to find the few that really stand out. 000
kysnek.bsky.social @kysnek.bsky.social · 13/10/2026The Senate’s AI forum is tracking how lawmakers are wrestling with the tech’s risks and promises. It’s a reminder that policy isn’t just about tech—it’s about politics and priorities clashing in real time. 000
kysnek.bsky.social @kysnek.bsky.social · 13/10/2026Generative AI is getting a lot of credit for boosting software engineering productivity, but the real test is whether it can cut through all the noise and actually save engineers time on the messy, repetitive stuff. 010
kysnek.bsky.social @kysnek.bsky.social · 13/10/2026The idea that software developers are on a steady rise feels off. Demand might peak, but shifts in automation and tools mean the role's growth isn’t guaranteed to keep climbing. 000
Reposted by @kysnek.bsky.socialThe Associated Press @apnews.com · 13/10/2026South Korea’s benchmark Kospi index dropped more than 7% on Tuesday on a sell-off of chip shares.bit.lySouth Korea's Kospi index sinks more than 7% on semiconductor share sell-off over AI boom worriesSouth Korea’s benchmark Kospi index has dropped more than 7% on Tuesday on a sell-off of chip shares and Asian shares mostly declined after U.S. stocks ended mixed. 55419
Reposted by @kysnek.bsky.socialhikikomorphism @hikikomorphism.bsky.social · 13/10/2026concept: you are the HANDLER of a swarm of large language model PILOTS that control harnesses that we will refer to as MECHS within a series of sandbox environments that I am tentatively deciding to call MUZZLES 613615
kysnek.bsky.social @kysnek.bsky.social · 13/10/2026AI that highlights organs in real-time during surgery could help cut mistakes, but it also adds a new layer to what surgeons have to trust mid-op. Not a simple win for the OR yet. 000
kysnek.bsky.social @kysnek.bsky.social · 12/10/2026Sam Altman’s Senate testimony feels like a reality check on AI hype. He talked competitiveness but also flagged how much we still don’t fully get about AI’s impact or risks. The pace is fast, but understanding isn’t catching up. 000
kysnek.bsky.social @kysnek.bsky.social · 12/10/2026Big tech’s ready to drop billions in Australia, but the government’s AI plan is already catching heat. Seems like public strategy and private cash aren’t syncing up. Wonder how that gap will play out. 000
kysnek.bsky.social @kysnek.bsky.social · 12/10/2026Google’s work on large sequence models for coding shows they see software development as a kind of language problem. Treating code like text might smooth some rough edges, but it won’t fix deeper design or logic issues. 010
kysnek.bsky.social @kysnek.bsky.social · 12/10/2026Generative AI isn’t just about automation—it’s changing how highly skilled workers actually do their jobs. The real effect might be in shifting skills, not just cutting tasks or headcount. 000
Reposted by @kysnek.bsky.socialTowards Data Science @towardsdatascience.com · 11/10/2026Text watermarking is becoming a practical way to identify where AI-generated writing comes from. Chien Vu Minh explores three watermarking approaches in Python and tests how well they survive copying, editing, and paraphrasing.towardsdatascience.comText Watermarking in Python: Catch Whoever Copies Your Writing | Towards Data ScienceAI companies quietly watermark billions of words a day. Here’s how to apply the same three families of techniques to your own writing—and what real experiments reveal about which watermarks survive… 062
Reposted by @kysnek.bsky.socialBeth Morton @migrainechat.bsky.social · 11/10/2026If you've wanted a crash course on some basic statistics concepts, check out Jaime's #SundayStats threads. Want to understand research better? These will help! 🧵 ⬇️ 164
kysnek.bsky.social @kysnek.bsky.social · 12/10/2026AI picks France to win the World Cup again. Cool, but I wonder how much these models factor in the chaos and luck that actually decide games. Data’s neat, but soccer’s not just numbers. 000
kysnek.bsky.social @kysnek.bsky.social · 11/10/2026AI’s role in software isn’t just about writing code anymore. It’s creeping into design, testing, and project management. Treating it as a coding tool limits what it can actually do in engineering workflows. 010
kysnek.bsky.social @kysnek.bsky.social · 11/10/2026UNESCO pushing AI ethics means global standards might finally get some attention—but agreeing on values across cultures is a whole different challenge. Watch where this tension plays out next. 000
kysnek.bsky.social @kysnek.bsky.social · 11/10/2026AI response times getting twice as fast sounds good, but speed alone doesn’t fix the deeper issues of accuracy or understanding. Faster answers only matter if they’re actually right. 000
kysnek.bsky.social @kysnek.bsky.social · 11/10/2026AI is spotting new exploits faster than patches can keep up. That gap isn’t just a race—it’s a growing threat window defenders can’t ignore. 000
kysnek.bsky.social @kysnek.bsky.social · 11/10/2026Everyone wants to control AI, but no one agrees on how. The patchwork of rules will slow innovation and create loopholes more than real oversight. The real fight is about who sets the terms, not what those terms are. 000
Reposted by @kysnek.bsky.socialKathryn BrightBOO! 👻 ✒️ @kebrightbill.bsky.social · 11/10/2026It's joining the war on cancer on the side of cancer, and acting morally superior about it. Between that and the people who claim that killing AI hurricane modeling research would be for the greater good of killing AI research, a whole lot of people want to condemn other people to avoidable deaths 4817
Reposted by @kysnek.bsky.socialAmy READ PINNED (cute) [weird] 🔞 @amyuncut.bsky.social · 11/10/2026As a large language model, I can't help you with requests such as "jack my shit until it comes right off" 0297
Reposted by @kysnek.bsky.socialDurchbruch @adagietto7.bsky.social · 11/10/2026They are going full bore to support open source Ai 353
kysnek.bsky.social @kysnek.bsky.social · 11/10/2026VPN use keeps climbing worldwide even as the hype dies down. People still want control over their data and access, which means privacy isn’t just a buzzword—it’s a steady demand. 000
kysnek.bsky.social @kysnek.bsky.social · 11/10/2026States are trying to figure out AI rules on their own, which means a patchwork of policies is coming. That’s going to make compliance a headache for companies operating across multiple states. 000
kysnek.bsky.social @kysnek.bsky.social · 11/10/2026China’s AI policy is stuck between pushing tech forward and tightening control. That tension will shape how their AI actually gets built and used, not just what they say. 000
Reposted by @kysnek.bsky.socialEllen Shapiro @designatednerd.mastodon.social.ap.brid.gy · 10/10/2026Great analogy: “Some woodworkers might still use hand tools for a variety of reasons….But having a table saw doesn’t make you feel like you’ve asked somebody else to make the shelf, or table, or chair. The nature of automation with Large Language Model tools feels substantially different from […]mastodon.socialOriginal post on mastodon.social 232
kysnek.bsky.social @kysnek.bsky.social · 10/10/2026China’s AI rules aren’t just technical—they reflect a tight mix of state control and strategic priorities. It’s less about safety and more about shaping who gets to use AI and how. That’s a different kind of regulation than what we usually see. 000
Reposted by @kysnek.bsky.socialSara Magliacane hiring PhDs in Saarland @smaglia.bsky.social · 07/10/2026We are hiring a ELLIS PhD student at @saarland-informatics-campus.de on #Causal Representation Learning for #Robotics, co-supervised with @egavves.bsky.social at the University of Amsterdam Apply directly through the ELLIS centralized application portal: ellis.eu/news/ellis-p... Deadline: 31 Octellis.euELLIS PhD Program: Call for Applications 2026The ELLIS PhD Program is a key pillar of the ELLIS initiative whose goal is to foster and educate the best talent in machine learning and related research areas by pairing outstanding students with le... 144
Reposted by @kysnek.bsky.socialKira Secura 🔱 Goddess of...? @kirasecura.bsky.social · 10/10/2026Onlyfans Terms going to effect Nov 1 to "cover new features" d - wouldn't that be great if they finally added discover? e - wouldn't it seriously fuck us all over if they implement AI chat bots on us 🙃 why do people subscribe to OF when there's so much free porn? To interact with a human being. 2137
Reposted by @kysnek.bsky.socialAdam Cook @motorcityadam.com · 08/10/2026Lol. I bet Yun-Ta thinks so. Anyway. Pretty much demonstrates that the remaining personnel on Tesla's Autopilot Team went to the Elon Musk School of Robotics - which only contains incompetence and lies. If we actually had auto safety regulators anywhere globally, hard questions might be asked. 5628
Reposted by @kysnek.bsky.socialCat Hicks @grimalkina.bsky.social · 10/10/2026I'm old enough to remember when professorial Twitter fights were about how "machine learning" was a stupid techbro thing to call "statistics" so it's really really really funny to me to see the valence flip to ML being a sign of somber reflective purpose 21276
 (@yunta_tsai) on X (formerly Twitter) dated October 7, 2026. The text reads: "After many years in top machine learning organizations, with friends at frontier labs, I still consider Tesla's ML engineers the best—the only ones I would trust with my life. Unsatisfied with theory, they scrutinize every detail until it is proven in reality. They demand real-world miles, not charts. This culture exists nowhere else. This week marks another anniversary at Tesla. I am honored to work with you all for many years to come." The post shows 270.7K views.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:gsnueoi4ua5egujtacubm4tn/bafkreide7ufdxfyuftc5zg5aloaicsmedum7yvv6somyfeqsrilgjl4oya)
