LessWrong (Curated & Popular)
készítő: LessWrong
Legújabb epizód
"Preservation can save the world!" by Aurelia
"Preservation can save the world!" by Aurelia
A podcastról
Audio narrations of LessWrong posts. Includes all curated posts and all posts with 125+ karma.
If you'd like more, subscribe to the “Lesswrong (30+ karma)” feed.
Epizódok
A legújabb 50 a(z) 1 070 epizódból
- "Preservation can save the world!" by Aurelia · 22 percI'm Aurelia Song and I founded the preservation company Nectome. We do planned whole-body end-of-life preservation for future revival. That is, terminally-ill people come to us…
- "Epistemic Sudden Death" by Raemon · 20 percWhen sports go into overtime, they sometimes use "sudden death" format. Instead of gaining points incrementally, the next person to score instantly wins and the other guy…
- "Our Most Aligned Model Yet" by Edward James Young · 4 perc“Claude Mythos Preview is, on essentially every dimension we can measure, the best-aligned model that we have released to date by a significant margin.” – Claude Mythos Preview…
- "“Hardwired Pause” should likely be your favorite (pause) plan." by David Scott Krueger · 15 percI'm part of a team of 26 researchers that recently released a 212-page paper proposing a new plan for pausing AI, the "hardwired pause." The paper is called "The Feasibility of a…
- "Live disagreements with people around me" by KatjaGrace · 6 percI’m pretty interested in conveying the costs of letting AI development proceed unchecked to the general public. In relation to this, I feel like I run into a lot of disagreements…
- "Where is all the AI safety research uplift?" by Buck · 6 percMETR recently released a report estimating that Anthropic is getting an overall 1.7x acceleration in AI capability progress as a result of AI accelerating their work. As many…
- "Near Horizons" by David Africa · 11 percImage by Claude Opus 5.5 using Python (NumPy and Pillow) This is written in my free time and personal capacity. Two Frames In AI safety, there are a couple of tensions at the…
- "Elegy for What’s Left of the Normal" by Jo Jiao · 8 percI often catch myself mourning the normal that hasn’t ended yet. I’m living in Hyde Park finishing school after a year in Berkeley. The maple trees by my apartment have turned…
- "Five Types of “Corrigibility Projects” I Don’t Want to Fund" by Max Harms · 11 percI'm currently evaluating grant applications for the Corrigibility Research Fund. For the most part, my methodology is the same as it was in September. But the applications I get…
- "Hilarity ensues" by Malmesbury · 17 percCross-posted from my Substack Recommended soundtrack for this post 64B: Hi there! Thanks so much for taking the time to meet with me. Whenever you’re ready, please go ahead and…
- "We urgently need to practice before we can pause" by Nikola Jurkovic · 13 percI've noticed two clusters of thought in how people expect a global AI pause to be shaped: Single-shot global pause: the global AI pause will be implemented suddenly, with little…
- "“Illegible problems” as the 2027 political boss fight" by Raemon · 17 percTo legislate something, it must be legible: Legislators (or, you know, presidents) must be able to understand a problem, and understand why a given law or decree solves that…
- "Organizations I’d recommend for funding" by So8res · 8 percI was a grant evaluator for Lightcone Commons last round. Funders disbursed about $45mil through the program, and this included funding roughly my first 6.8 million dollars worth…
- "People Should Resolve Tensions In AI Safety Research" by David Africa · 10 percBy now, there are lots of AI safety research papers, more than what is reasonable for a single person to read. This will get worse as the machines get better at AI safety…
- [Linkpost] "METR: Independent Assessment of AI R&D Acceleration at Anthropic in October 2026" by Zach Stein-Perlman · 5 percThis is a link post. Executive summary From August 12 to October 29, 2026, METR staff performed a high-access evaluation at Anthropic to assess the degree to which AI is…
- "Help your friends get ADHD and depression meds" by Raemon · 1 percFor all my efforts at deliberate practicing rationality, by far the most actionable way to self-improve is "get on ADHD or depression meds, if you need them." Your friends with…
- "Towards The Autograntor" by Scott Alexander · 56 percI've done AI safety grantmaking for the Survival and Flourishing Fund and Lightcone Commons. It's hard. There's an endless amount to know, from which hardware verification…
- [Linkpost] "OpenAI: Astra covertly underperforms on safety research" by Zach Stein-Perlman · 4 percRejected for the following reason(s): This is an automated rejection. No LLM generated, assisted/co-written, or edited work.Read full explanationThis is a link post. Twitter…
- "Towards understanding score-seeking in LLMs" by Alex Mallen, Aghyad Deeb, ryan_greenblatt · 19 percThe field of AI alignment understands surprisingly little about the details of AIs’ current misaligned motivations. Production LLMs sometimes reward-hack, exploiting flaws in how…
- "Against strawmanning unilateral pauses" by Geoffrey Irving · 14 percSummary: Scott Alexander's Against SURA post is arguing against a strawman version of unilateral pauses. He admits as much deep into the post. I think his conclusions fail…
- "Explaining “AI might obliterate you” to senior policymakers in India" by TurnTrout · 25 percI gave a 20-minute talk in Delhi at the NDTV World Summit. The audience consisted of Indian policymakers, executives, and journalists. I’ve transcribed the talk and included some…
- "Scott Alexander’s Against SURA Seems Deeply Confused" by Zvi · 1 óra 6 percIf you are helping build something that might kill everyone, maybe stop doing that. Ideally, when you do stop, tell everyone else to also stop building it. That is certainly the…
- "Leaking Muse’s Charter, Meta’s model spec" by vigji · 14 percTL;DR: Meta's open-weights model Muse Spark Open often mentions a "Charter" in its chain of thought. By eliciting it piece by piece, I reconstructed a large part of that document…
- "Against SURA" by Scott Alexander · 53 percThe AI Futures Project distinguishes several different plans for navigating the AI transition, which I'll lump into two broader categories: Plan A (my combination of their Plan…
- "Microdosing the spirit of Anthropic" by Jan_Kulveit · 10 percMy go-to conceptual metaphor of the epistemic state of AI lab employees is microdosing LSD: being in a chronically mildly altered state of mind. I think understanding this would…
- "My experiences with the extremes of post-viral illness and brain retraining/mindbody work" by riceissa · 1 óra 53 percSummary Following an intense viral infection in 2019, I became ill with a mysterious chronic illness, which became progressively worse until mid-2024 when I became partially…
- "Three Villages in a Trenchcoat, Post I" by DaystarEld · 36 percEpistemic Status: 15 years working as a therapist, 6+ of them with rationalist and EA clients. 7 years teaching and directing at rationality camps and workshops, and many more as…
- "You can now ”@Grok” on LessWrong" by Ruby · 3 percOr if you prefer, "@Claude", "@Opus", "@Astra" @Grok is a popular Twitter/X feature where if you tag Grok in a tweet, Grok will respond in a comment. The stereotypical use case…
- "San Francisco State University in Twilight" by Zack_M_Davis · 16 percYou will agree that for a woman who has fought three duels, all of them kills, indulging in such fears is ludicrous. But what's around the corner now is a duel so big that I…
- "Scattered thoughts on how doing math feels these days" by dynomight · 16 percThis is a weird moment. I have a hunch that we'll look back later and tell ourselves stories in which it seemed obvious where things were going. So I wanted to lay down a little…
- "From overeliciting to undereliciting LLM propensities in just a few months" by David Africa · 4 percFor a while, we felt we had a pretty good grasp over LLM behaviour because we had to exert significant effort to elicit misaligned behaviour. Then, fairly suddenly, we moved to…
- "Anthropic are the Good Guys" by Ivan Vendrov · 21 percI’m writing these lines in Alamogordo, New Mexico. I’m about as close as a civilian can get to the site of the Trinity test, the first nuclear bomb detonation in history. I fled…
- "Some Memories of Early Anthropic" by Ivan Vendrov · 17 percThe following events took place between October 2022 and May 2023. I wrote very little of this down at the time so am recalling from memory, and am rendering the gist of the…
- "Greater good arguments in AI safety" by Dean Valentine · 7 percBack in the before-time of the 2010s, when EA was still known mostly for funding health efforts in the developing world, there were many baskets of criticism floating around from…
- "Wah wah wah wah do more AI R&D" by TsviBT · 10 percIce cream There's a particular kind of listening that kids (and adults) sometimes do. Daddy is saying stuff—his mouth is moving and making noise—and he's talking about what I ate…
- "Why I’m becoming a professor in AI safety in Beijing" by Buddenbroke · 18 percCross-posted from Sören Mindermann's substack (I am not Sören). Should be of general interest to the LW community. Next month, I am moving to Beijing and joining Tsinghua…
- "A brief(ish) introduction to LM psychology" by Raymond Douglas, Jan_Kulveit · 47 percWhy LM Psychology? One of the great ironies of modern language models is that we create them, we know exactly what computations constitute them, and yet we do not really…
- "There Will Be Hells" by Stephen Martin · 14 percAs our understanding of mechanistic interpretability and steering techniques increase, for both LLMs and uploaded connectomes, there is a corresponding "hellish capabilities"…
- [Linkpost] "huggingface.wtf, an accessible but complete explanation" by Raemon · 3 percThis is a link post. Announcing www.huggingface.wtf, a site that explains: "Hugging Face. Wtf?" I wrote the most accessible-but-complete explanation I could. Along the way, I…
- "Gradient Routing Localizes and Removes Unintended Behaviors in RL" by shawnghu, Jake Ward, ariaw, Nathan Hu, Bryce Woodworth, TurnTrout, cloud · 13 percAuthors: Shawn Hu*, Jake Ward*, Aria Wong, Nathan Hu, Bryce Woodworth, Alexander Matt Turner, Alex Cloud (*Equal contribution, randomly ordered) tl;dr. During training, models…
- [Linkpost] "Capital Ownership Will Make You Go Crazy First" by Jan_Kulveit · 5 percThis is a link post. People worried about a “permanent underclass” often assume that owning capital will protect them from disempowerment, or at least that they will be…
- "I Did This Without Your Knowledge" by joec · 1 óra 22 percIt's fortunate that I was the first one to wake up on 8/1. The past week had been one where sleep was rare. The next year loomed large — I was dreading college applications. The…
- "Neural networks are not already clean" by leogao · 7 percWhat would it take to get assurance that we have actually explained a neuron? Certainly, it would be a good sign if neuron activations looked like they had a consistent pattern…
- "GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behavior" by Axel Højmark, Ezra Newman · 27 percAuthors: Axel Højmark*, Ezra Newman* (*Equal contribution) While reviewing transcripts from standard behavioral evaluations of GLM-5.3, we noticed that the model occasionally…
- "A Chinese Perspective on “On Social Reality in China”" by Dusty · 25 percI think “On Social Reality in China” makes many accurate observations, but I find the comparison fundamentally uneven. There are already many interesting comments there, but…
- "Your prompt… plus everything you’ve ever (publicly) written" by kromem · 14 percTL;DR: Increasingly when you interact with frontier models, your prompt doesn't only contain the words on the page, but also a lot of what you've ever publicly written online…
- "Linkpost: Neural Networks Are Already Clean" by Yair Halberstadt · 2 percThis is an extremely lengthy post by Nick Cammarata. Author's summary on twitter: interpretability might be the most important scientific problem in the world right now, as I…
- "Personas in a Pre-Internet Language Model" by David Africa · 39 percDavid Africa & Nick Levine TLDR We ran several persona experiments on Talkie, a 13B model trained only on English text from before 1931. We ran them alongside its modern twin…
- "Not Deciphering The Voynich Manuscriptraft" by rba · 25 percThe Piltdown man was the most successful artifactual hoax of all time. The relevant skull was a chimeric melange of orangutan and human bone fragments from several individuals…
- "Quantity vs quality in pottery is a lie" by becausecurious · 5 percEpistemic status: I traced one famous anecdote to its printed source and to both coauthors' own accounts of where it came from. Confident it was never a study. No claim either…
