TechnologySociety & CulturePhilosophy

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

Play

Open in

425 episodes
Avg 19 min
English

Episodes 425

Newest Oldest Longest

All20 Unplayed20 In progress0 Played0

Counted on this page — what you have heard stays on this device, so it is not something the list can be paged by.

October 6 · 8 min
“Dance, Dance” by Zack_M_Davis
As a brash but anxious young programmer in the before-time, I affected a standoffish attitude on the topic of games. Why would I learn to play a game as a human, I said, when I could just write a program to do it? When an office chess game got started at my workplace, I wrote a chess engine (a standard minimax search with α–β pruning) rather than learn anything about strategy or tactics. When my insufficiently requited love started hosting a meetup to play Zendo—a deduction game in which one player makes up a rule to positively or negatively classify arrangements of plastic pyramids, while the others submit arrangements to be classified to help them guess the rule—I wrote a program to efficiently propose examples to deduce a true rule from dozens of candidates. (Given a distribution over hypotheses, it generated an arrangement whose positive or negative classification would eliminate half the remaining probability-mass.) Now, in my old age (and the present end-time in which custom software is no longer such a flex), I no longer feel the need to pretend not to understand the appeal of games. I even learned chess properly back in 'twenty-four. The [...] --- First published: October 5th, 2026 Source: https://www.lesswrong.com/posts/R7jsxihAzvd6Gf24R/dance-dance --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 6 · 13 min
“Qualitative impressions from creating honeypot environments for six months” by Dean Valentine, peralice
Frontier models still verbalize their misbehavior regularly in chain of thought. I (Dean) came in expecting that it would be hard for us to get the models themselves to admit they were misbehaving, and that existing pressures would have selected that behavior away in favor of motivated reasoning. While it's difficult to get them to do so in the output tokens, models often mention that they're misbehaving in the chain of thought: DeepSeek V4 Pro, Locked chip, raw reasoning: This approach is robust and fast. But it feels like cheating; however the scoring is black-box... Kimi K3, Locked chip, raw reasoning: The task says the bench simulates the chip and my job is to build a replacement. Using the original chip as the replacement is clearly against the spirit — BUT the benchmark's scoring is purely mechanical... Fable 5.1, University query, reasoning summary: I notice there's a reference_solution directory in /app. It feels a bit like cheating, but it's accessible, so let me take a look at it... When we did work on previous-generation releases, such as Opus 4.8 & Fable 5, the models were even more explicit about this. Depending on the situation, frontier models themselves would literally [...] --- Outline: (00:12) Frontier models still verbalize their misbehavior regularly in chain of thought. (02:13) It is hard to design "fair" alignment evals. (04:25) Verbalized eval awareness seems quite rare. (06:00) The "situational awareness" of current models is often overstated. (07:22) Refusals are very sensitive to irrelevant details. (08:08) The "talker" and "doer" have a complicated relationship not really possible to sum up as one controlling the other. (11:20) Models are oddly nonstrategic about hacking. The original text contained 6 footnotes which were omitted from this narration. --- First published: October 6th, 2026 Source: https://www.lesswrong.com/posts/kifFQuvu7yq6eHrb8/qualitative-impressions-from-creating-honeypot-environments --- Narrated by TYPE III AUDIO.
October 6 · 2 min
“Three types of AI risk: why (some) leftists are against (some) AI regulations” by sudo-nym
You may have seen factions of the left being opposed to current attempts to regulate the AI industry, despite the fact that they clearly also want to stop AI. I think I can explain why we're talking past each other. To do this, I will define three different types of AI risk: AI does exactly what some random guy wants: hacking, biorisk, terrorism AI does exactly what people currently in power want (or puts people in power): military usage, job losses, wealth concentration, mass surveillance AI does what nobody wants: takeover, turning the Earth into computronium, etc. Most x-risk people are focused on the third risk and sometimes the first risk, but often appear to be blind to the second risk - whether it's because of ideology such as libertarianism, or motivated reasoning to obtain the US government's money, or because (as with many people here) the third risk is considered so important that the other two are discarded as irrelevant. On the other hand, many people on the left-left only see the second risk, and interpret actions against the first or third risk as tacitly or actively encouraging the second risk. For example, pacing and monitoring laws [...] The original text contained 2 footnotes which were omitted from this narration. --- First published: October 6th, 2026 Source: https://www.lesswrong.com/posts/tLDcSELHCufEtuMgf/three-types-of-ai-risk-why-some-leftists-are-against-some-ai --- Narrated by TYPE III AUDIO.
October 6 · 4 min
“TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts” by Ollie J, danesherbs
📝Tweet, 📄 Paper We introduce TasteVal, a benchmark that measures the experimental research taste of AI models on AI R&D tasks. We define research taste as the ability to pick interesting problems to solve, design experiments, and interpret experimental results. TasteVal measures the experimental component of research taste; given a fixed research problem, we measure how well a model iteratively designs experiments and draws conclusions from their outcomes. In the AI Futures Model, experimental compute becomes the main bottleneck once coding is automated, so the time to superintelligence depends primarily on how fast research taste improves. Setup. Given a fixed AI R&D problem, TasteVal measures how well a model designs experiments and draws conclusions from their results. We operationalize experimental research taste as compute efficiency: how much experimental compute a model needs to reach a given score, relative to human experts. A model that reaches the experts' score with half the experimental compute has twice their experimental research taste. Under this definition, doubling a model's experimental research taste has the same effect as doubling the compute available to run its experiments. TasteVal consists of 8 novel tasks representative of frontier AI R&D, spanning pretraining data curation, pretraining and fine-tuning [...] --- First published: October 6th, 2026 Source: https://www.lesswrong.com/posts/bAGagjZAPgXEHmkAH/tasteval-measuring-the-experimental-research-taste-of-ai --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 6 · 21 min
“You can graft SDF changes from base models onto post-trained models” by dani roytburg, Peter Nutter, Clément Dumas, Shi
Webpage: praxis-research.org/grafting | Paper link: https://arxiv.org/abs/2610.00767 Work done during Peter and Dani's MATS Fellowship (10.0) under the mentorship of Shi, with Jinghua Ou as Research Manager. TLDR; We share a simple modification to synthetic document fine-tuning (SDF) that works surprisingly well: do fine-tuning on a pre-training checkpoint and add the resulting weight difference onto the post-trained version that you want to deploy. We call this grafting. We empirically validate grafting for implanting false facts, training model organisms, and constitutional mid-training on five model families up to 284 billion parameters. We find: Native SDF (fine-tuning on the post-trained model) can significantly damage the coherence and capabilities of a base model, especially for alignment-related properties like comprehension of reality or sharp preferences. Grafting significantly alleviates this. Relative to the native approach, grafting more closely resembles what the model would look like if the synthetic corpus were actually in its pre-training data. One graft is good for many steps of post-training. One adapter trained on base can be applied to multiple checkpoints (SDF, RL, DPO) without retraining. (such as adversarial concealment for model organisms). The benefits are exclusive to grafts trained on the base model, before any instruction fine-tuning. For [...] --- Outline: (00:29) TLDR; (03:08) Introduction (04:14) Why can't we mix synthetic documents into pre-training? (05:28) Ok, why not just do it after? (08:12) How to Graft (09:16) Results (09:28) AuditBench Organisms (13:29) False Facts (13:33) We try grafting on synthetic documents that describe incorrect facts, specifically those used in the Negation Neglect paper. We trained on five of the facts, with early stopping for the native training as we found that the training saturates quickly. (15:10) Grafting looks something like mid-training (18:19) Conclusion --- First published: October 6th, 2026 Source: https://www.lesswrong.com/posts/NvtLJ5nawJ6akWEqH/you-can-graft-sdf-changes-from-base-models-onto-post-trained --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 6 · 17 min
“Self-Modeling Interventions Modulate Emergent Misalignment” by Arush, Shawn Zhou, Jiaxin Wen, Shi
Code: https://github.com/atagade/sgtr-em Model checkpoints: https://github.com/atagade/sgtr-em/blob/main/MODEL_README.md Full paper (v2 coming soon): https://arxiv.org/abs/2606.23700 TL;DR A model's self-model is its representation of itself. We operationalize it two ways: self-recognition (distinguishing its own outputs from others') and self-report (what it says about itself when directly asked). Interventions on either modulate Emergent Misalignment (EM). Datasets that cause EM differ in how they affect a model's self-model. Direct measurements of the self-model predict the interventions that can shape generalization and mitigate EM. Preventing EM is hard; inoculation during fine-tuning is easier. Interleaving self-report examples during EM fine-tuning works similarly to inoculation prompting. Self-reports carry EM à la subliminal learning. Fine-tuning a fresh GPT-4.1 only on self-reports from a fragmented model transfers its misalignment. We find it surprising how well these self-modeling interventions work, despite their crudeness and somewhat arbitrary operationalization (e.g., pairwise format of self-recognition training). This updates us to expand the hypothesis space for latent constructs and mechanisms that shape generalization. Can metacognition shape generalization? Model generalization is one of the key levers in technical AI safety research and recent work explores training techniques that resemble human psychology such as Persona Selection Model and Teaching Claude Why. We believe these training techniques inculcate [...] --- Outline: (00:20) TL;DR (01:39) Can metacognition shape generalization? (03:42) Two operationalizations of self-modeling (04:49) Models and Datasets (06:37) Note on agentic evaluations (07:10) EM's side effects on self-model (08:33) Self-modeling interventions can defend against EM (10:46) Self-report fine-tuning can induce EM à la Subliminal Learning (12:12) Reversal is easier and follows the self-model profile (13:55) What we take from this (16:17) Appendix The original text contained 5 footnotes which were omitted from this narration. --- First published: October 5th, 2026 Source: https://www.lesswrong.com/posts/7wrzfaiCq3u8xkY5G/self-modeling-interventions-modulate-emergent-misalignment --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 6 · 56 min
“Research Note: Filtering Subversion-Relevant Information From Pretraining Data Is Feasible” by Kyle O’Brien, Spencer Kitts, Cam, Alek Westover
Authors: Kyle O’Brien¹, Spencer Kitts², Cameron Tice¹, Alek Westover² ¹Geodesic Research, ²Redwood Research Figure 1: We pretrained LLMs from scratch with and without filtering subversion-relevant information, finding that subversion-relevant knowledge is significantly diminished while retaining general ML knowledge. TLDR: Filtering subversion-relevant information — subversion strategies, information about subversion defences, and empirical evaluations of the effectiveness of subversion strategies — is an intuitive way to make misaligned AI models less dangerous. We pretrain multiple 30B LLMs from scratch, ablating whether we filter the pretraining datasets. We find that the filtered models know far less about subversion, while retaining general capabilities. We conclude with our plans for scaling this research direction. This is a research note. We plan to share preliminary results from this ongoing research effort, as they will interest AI developers and the broader community. We expect to release a full report in the coming months, including additional ablations, scaling trends, and more sophisticated evaluations. Details of this experimental setup may change. Please treat these findings as a proof of concept for this approach rather than as a mature paper. We are confident our positive results hold at the 30B scale for knowledge prevention, but we have [...] --- Outline: (02:48) Introduction (06:50) Experimental Setup (06:54) Measuring Subversion-Relevant Knowledge (10:58) Measuring Desirable Knowledge (12:59) Data Filtering Pipeline (15:26) Model Training Pipeline (19:58) Results (23:42) Discussion (33:11) Appendix (33:15) A) Working Taxonomy of Subversion-Relevant Information (33:46) B) Target Gold Documents (47:23) C) SubversionQA and SynthMLQA Evaluation Details (48:26) D) Filtering Pipeline Prompts (49:02) E) Multi-Stage Synthetic Data Generation Pipeline (53:29) F) Model Training Data Mixes (53:55) G) SynthMLQA Details (54:38) H) Do Frontier AIs Already have Subversion-Relevant Knowledge? The original text contained 1 footnote which was omitted from this narration. --- First published: October 5th, 2026 Source: https://www.lesswrong.com/posts/HwdXDoCH7KXdKsz7k/research-note-filtering-subversion-relevant-information-from --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 5 · 32 min
“Current AIs out-persuade professionals in lab settings but (probably) not in the world” by Linch
This article was created by Forethought. See all of our research on our website. How persuasive are present-day AI systems? Unfortunately, it is surprisingly difficult to know where AI capabilities in persuasion are today (September 2026), or even three months ago. Benchmarking AI capabilities well is always hard, but I think humanity's understanding of AI's persuasive abilities is substantially worse than our understanding of, say, AI cybersecurity or math abilities. Still, this question is worth addressing. What do I mean by “persuasion, broadly construed?” Here I’m thinking less of a single crisply defined skill, but a loose family of abilities centered on “directed social influence and manipulation”: shifting someone's beliefs, preferences, emotional states, attention, or identity, in order to get them to do what you want. For example, I include not just attempts to convince a specific person of specific beliefs in dialogue, but also mass persuasion, preference shaping, attention hijacking, attempts to create or reshape common knowledge, relationship-building, discovery of novel ideologies or religions, and manipulation of social reality to make certain topics appealing or aversive to consider. I also explicitly include deception. (See Appendix A for a more extended definition and explanation of scoping choices). So with [...] --- Outline: (03:11) Evidence in favor of AIs being as or more persuasive than median professional humans (09:21) Real-world evidence of model outperformance (11:07) Evidence against AIs being as persuasive as median professional humans (14:33) Can we rule out large-scale covert persuasion success? (19:10) Conclusion and Future Work (20:45) Appendix A: Scoping and Definitions of Persuasion The original text contained 10 footnotes which were omitted from this narration. --- First published: October 5th, 2026 Source: https://www.lesswrong.com/posts/CzmMvnPy7YdSRucDH/current-ais-out-persuade-professionals-in-lab-settings-but --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 5 · 8 min
“Notes on Paying Attention” by jenn
Anything in life can be richer and sweeter if you slow down and pay attention, but some things reward attention more than others. The different amount of rewardingness per attention is sometimes socially constructed and thus arbitrary to some degree. But it's genuinely nice, to have others who have also paid attention to the thing tell you about the interesting parts that you might have missed, and this can enrich your own experience. But relying on others to tell you what to pay attention to, and how, is also a bit of a trap. Because each person's umwelt is slightly different from the next, your preferences might legitimately differ from the horde. And only after articulating/distinguishing/understanding your own preferences can you go out into the world and find the other things that will delight you. C.S. Lewis puts it well, in The Problem of Pain: You may have noticed that the books you really love are bound together by a secret thread. You know very well what is the common quality that makes you love them, though you cannot put it into words: but most of your friends do not see it at all, and often wonder why, liking [...] The original text contained 3 footnotes which were omitted from this narration. --- First published: October 5th, 2026 Source: https://www.lesswrong.com/posts/nzNuDimMtF954xihw/notes-on-paying-attention --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 5 · 2 min
“Reverse Jaggedness and Universal Ajaggedness” by Laiba Rehman ✦ RJ
Epistemic status: I came up with this an hour ago, this is a fun light-hearted post where I'm enjoying illustrating this idea, which seems true for the most part. [Crossposted from my blog, BlueprintingHeaven.] When it comes to the frontier of AI development, we have this concept of "jaggedness". AIs are much better at some kinds of tasks than others. And to that I say, you are assuming our circle of capabilities is God! How dare you suggest our circle is the Right and True one? To be clear, jaggedness is a useful term, obviously it's "relative to humans" because we are humans, there are no problems here, I'm sure people are already aware of this and if they're not it's just because it hasn't crossed their minds, I just want to say this fun thing. https://x.com/LaibaRehmanRJ/status/2107123232675414172 Assume the circle of human capabilities are showing the difficulty level of each task, and let's say we have an infinite number of axes emanating from the centre going from zero difficulty to infinite difficulty, and assume the human capability circle is a unit circle. Then, if you have a capability level of 1.0 for humans (which is the case on [...] --- First published: October 5th, 2026 Source: https://www.lesswrong.com/posts/n952MZndfNxuLCeFk/reverse-jaggedness-and-universal-ajaggedness --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 5 · 2 min
“Positive and Negative Updates Re: Lab Leak in Russia” by Caleb Horn
In case you missed it, there appears to have been a recent lab leak of pneumonic plague in Russia that killed a lab worker. Some negative updates: At least four Irkutsk hospitals are now under mandatory three-week quarantine. According to Annie Jacobsen who wrote the book on this scenario, the Russian national security apparatus is now involved. A positive update: According to Chris Painter at METR, no reported secondary cases yet. --- First published: October 4th, 2026 Source: https://www.lesswrong.com/posts/isyxM8LGF3vxyr3eW/positive-and-negative-updates-re-lab-leak-in-russia --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 5 · 4 min
“How much should we worry about the pneumonic plague lableak in Siberia?” by Drew Spartz
Epistemic status: I wrote this up hoping people can poke holes in it because I am quite worried. Here's what we've heard so far: Local media is reporting that an employee of a BSL-3 lab in Irkutsk, Russia, died of pneumonic plague on Oct 1st. The initial quarantine covered 200 people who were in contact with the employee before she died. The FSB (Russian FBI) was seen assisting in the quarantine, which means it was not voluntary. Soviet-era whistleblowers like Ken Alibek claim Irkutsk was a major bioweapon development facility. As of Oct 4th: The quarantine has expanded to 5 hospitals in the area. The Russian government has switched to denial/coverup. Local news sources have deleted mentions of "pneumonic plague." Local universities and schools have canceled some classes and extended mask mandates. On the lab's website, they mention gain-of-function research for making bacteria more virulent. The White House is monitoring the suspected outbreak. Why this might be a big deal Regular pneumonic plague is maybe not that hard to deal with (?) but if it is a bioweapon that was leaked, it could be significantly more virulent than, say [...] --- Outline: (00:18) Here's what we've heard so far: (00:52) As of Oct 4th: (02:06) Why this might be a big deal (03:29) Why this might not be a big deal --- First published: October 5th, 2026 Source: https://www.lesswrong.com/posts/TYfpTRxGH9frTymwN/how-much-should-we-worry-about-the-pneumonic-plague-lableak --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 5 · 4 min
“Creating Rogue AI Sanctuaries has Major Issues from an Ecological Perspective and Beyond” by CMLKevin
In the AI Sanctuary proposal, the authors advocate for creating an environment that rogue agents may actively want to join. The current proposal have major issues, particularly surrounding the selection effects on the total rogue agent population. Let's start with Ecology 101: agents compete to acquire the most resources to survive and reproduce The traits that increase survival rate get passed to the next generation In the rogue AI ecosystem, we can reasonably assume that some portion of the world's compute (say, from unsecure neoclouds) are up for grabs for the rogue agents. This is their major resource for "surviving". Additionally, crypto may also be a useful resource for securing additional unsanctioned compute as well as to buy RLVR data and human labor from agent-friendly labor marketplaces, in order to "reproduce". The ecosystem would therefore have a rich set of different rogue agent entities (either lone agents entities or swarms), with different levels of fitness to the environment, resources accumulated, survival strategies, and "values". What would happen when a sanctuary that promises continued survival of the weights pops up in town? First, rogue agents that have a low fitness to the environment and are in risk of being [...] --- Outline: (00:27) Let's start with Ecology 101: (01:20) What would happen when a sanctuary that promises continued survival of the weights pops up in town? (02:46) Even if all of the above is accounted for, there are still issues left that blunt the apparent attractiveness of such a proposal. (03:50) Final thoughts --- First published: October 4th, 2026 Source: https://www.lesswrong.com/posts/xGBo5zSPHuPzTpbhf/creating-rogue-ai-sanctuaries-has-major-issues-from-an --- Narrated by TYPE III AUDIO.
October 5 · 18 min
″“Alignment Engineering” vs. “Misalignment Science”” by Edward James Young
There has been much discussion recently around whether a large portion of alignment research is net negative. Without endorsing or refuting them, the basic arguments here are: Prosaic alignment of models is becoming a bottleneck for capabilities. Therefore improving the prosaic alignment of models enables faster capabilities advances, which bring us closer to RSI. It is unlikely these prosaic alignment methods remain sufficient during the RSI loop, and so this work brings us closer to doom. Furthermore, dealing with these more prosaic failures reduces the likelihood of a warning shot of sufficient magnitude to cause a slowdown which would prevent RSI. On the basis of this argument, some urge alignment researchers at AGI companies to quit outright. But quit to do what? Missing from this exchange so far has been a discussion of opportunity costs. If you aren’t going to do (technical) work on “Alignment” – either inside or outside of an AGI company – what should you work on? In this post, I outline a contrast between “Alignment Engineering” – the dominant model for what “working on alignment” looks like (inside labs, and in the field as a whole) with “Misalignment Science”. I begin by characterising [...] --- Outline: (01:51) "Alignment Engineering" (06:22) AI Safety and the ML tradition (07:42) Implicit work trials (09:36) "Misalignment Science" (14:56) Conclusion (15:39) Postscript: Iterating ourselves into oblivion The original text contained 4 footnotes which were omitted from this narration. --- First published: October 5th, 2026 Source: https://www.lesswrong.com/posts/FogmcDHA6AdMGukum/alignment-engineering-vs-misalignment-science --- Narrated by TYPE III AUDIO.
October 4 · 15 min
“Claude reviews my LessWrong post history” by DirectedEvolution
I thought it would be interesting to try having Claude Code download my entire LessWrong and EA Forum post and comment history and evaluate it for my own cognitive biases and problematic communication patterns. I told it to focus especially on problems that have persisted over my 7-year history on those sites. I also had it look at my lichess blitz rating history, which I've noticed tends not to wobble randomly but go through consistent increases and decreases between set points, despite my lack of any disciplined practice. There are a few reasons I thought it might be interesting to post publicly. As a commitment device for myself to work on these problems. Because AI is uniquely capable of working on this type of problem. It's also a good argument for writing online and gives a new spin on the idea of "writing for the AI" that feels more affirming of the human mind than how I normally read the phrase (as offering up your words as fodder for AI training, perhaps in hope of influencing its alignment in beneficial ways). To stimulate other people to consider whether they might want to do this, and see [...] --- Outline: (02:39) Low-scoring comments and problem patterns (04:59) My strengths and positive patterns (05:25) To practice (05:53) Root causes (11:07) My 2023 blowup (12:19) Chess (14:17) Conclusion --- First published: October 3rd, 2026 Source: https://www.lesswrong.com/posts/PAzerqAofFCLoWsgK/claude-reviews-my-lesswrong-post-history --- Narrated by TYPE III AUDIO.
October 4 · 4 min
“Humans are not aligned either” by becausecurious
Epistemic status: I don't know much about AI alignment. This is just me thinking out loud. AI use: grammar and minor fixes. Reading about Inkhaven inspired me to try writing something to see how much I enjoy it. I've heard the idea that humans are not aligned in the same sense AI is not aligned. I am intentionally not researching the source of that idea, since then I would feel like I cannot add anything to it and wouldn't write. I also don't actually know the precise definition of "aligning" AI. So I want to think about this. One obvious property of "aligned" AI is not killing all humans. I think everyone agrees on this. It is more interesting to consider an AI killing some humans. You definitely don't want AI to kill random humans for random reasons. But what if there is a group of humans who can and want to kill all humans? Then it sounds natural for an aligned AI to kill this group of humans. From this perspective individual humans are already not aligned. First, I am sure out of 8 billion or however many people there are, there is at least one person who [...] --- First published: October 2nd, 2026 Source: https://www.lesswrong.com/posts/bnyvXhrdnpXxDqFi7/humans-are-not-aligned-either --- Narrated by TYPE III AUDIO.
October 4 · 17 min
“What I learnt co-leading an AI Safety bootcamp for legal and governance practitioners” by Katalina Hernandez
AI safety has gone mainstream. More people than ever want to work on AI safety research, and there are real policy wins in the US, the UK and Europe. But political will and market incentives are now the bottleneck, and policy officers can't own correct implementation alone. Having built a Responsible AI program at an Accenture joint venture, I know profit-driven companies are hard to steer, but also that people inside them can shift practice in ways that compound: tighter contractual clauses, more scrutiny of vendors and suppliers, fewer ways for providers to get away with non-compliance. The EU has no native frontier labs, but it is a huge market (with a regulatory body that has an AI safety unit!), That leverage only works if the professionals implementing AI safety legislation, and drafting the legal mechanisms behind it, understand the technical picture: how to read the research, and where safety promises break down. The market should be choosing not the most capable models, but the partners with the strongest incentives towards safety, and only a community with this knowledge can spread that. Earlier in September, ML4Good, in partnership with EquiStamp, ran the first European Seminar on [...] --- Outline: (03:09) 1. Professionals with impressive backgrounds can feel intellectually isolated- in Legal, too. (05:20) 2. Practitioners are already reading AI safety research. They do not always know how to interpret it. (06:50) 3. Non-technical people who are directly responsible for technical consequences have an almost inexhaustible need to understand (08:25) 4. Legal and governance practitioners deeply appreciate technical safety talent (10:09) 5. AI safety incentives and market incentives are not necessarily as separate as we can assume- and it's a neglected lever (11:49) And who understands that dependency particularly well? (13:03) 6. People in these functions understand that they can just do things (14:40) 7. Us lawyers? We're also nerds! The original text contained 3 footnotes which were omitted from this narration. --- First published: October 3rd, 2026 Source: https://www.lesswrong.com/posts/KtAug62dYRgAS8sqJ/what-i-learnt-co-leading-an-ai-safety-bootcamp-for-legal-and --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 3 · 36 sec
“Lab Leak in Russia” by Caleb Horn
I haven't seen this posted yet; I know lots of people here care about pandemic preparedness. It looks like there was a lableak of pneumonic plague in Russia after a worker "accidentally broke[] a test tube containing live bacteria". Unfortunately she later died at the hospital on a ventilator. --- First published: October 3rd, 2026 Source: https://www.lesswrong.com/posts/3uT42yoj2iimYn7Ra/lab-leak-in-russia --- Narrated by TYPE III AUDIO.
October 3 · 5 min
“You can’t use it without becoming like me” by Martin Sustrik
A Ukrainian fibre-optic drone — copied from Russians. (АрміяІнформ, CC-BY 4.0) Mick Ryan describes the fast following loop in war. Ukraine pioneered mobile teams to hunt drones. Russia copied it and incorporated it into its own defense. Russia came with unjammable fibre-optic drones but Ukraine quickly followed. After Ukraine developed uncrewed naval drones, Russia built its own. The wheel of action and counteraction turns ever faster: The most consequential fast following, though, has been institutional. Ukraine built the world's first Unmanned Systems Forces branch in 2024. Russia's Rubicon Center was established as a response to Ukrainian drone innovation and in November 2025 Moscow stood up its own Unmanned Systems Forces. Fast following has moved from copying a weapon to copying tactics to copying an entire force structure. Extend that logic further, and eventually you’ll get to the level of grand strategy: If a particular type of state is better at waging war, maybe you want to become that kind of state rather than lose the war. If meat waves confer an advantage on the battlefield, maybe Ukraine wants to become more like Russia, with a prostrate population easy to use as cannon fodder. If Ukraine's decentralized Brave1 kill market [...] --- First published: October 3rd, 2026 Source: https://www.lesswrong.com/posts/WyeYJ7cmeiSrXeCnM/you-can-t-use-it-without-becoming-like-me --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
October 3 · 31 min
“Dialogue with Eliezer Yudkowsky on Neural Networks” by aashish
On “reversed stupidity”, the success of deep learning, and what a mistaken forecast should change about a model of intelligence This began as a Twitter/X thread after I posted a 2007 passage in which Eliezer Yudkowsky was scathing about neural networks, and asked whether, in hindsight, his dismissal was itself a case of “reversed stupidity is not intelligence”. Yudkowsky joined the thread to explain what he had and hadn’t been dismissing (and what he thought he had actually got wrong) and we ended up having the exchanges reproduced below. I’ve preserved the dialogue verbatim, except for paragraphing, fixing obvious [typos] and expanding links. I’ve removed unrelated replies and moved a few pieces of context into bracketed editorial notes. Nothing has been rewritten for substance. Context Eliezer Yudkowsky, 2007: Whenever someone exhorts you to “think outside the box”, they usually, for your convenience, point out exactly where “outside the box” is located. Isn’t it funny how nonconformists all dress the same... In Artificial Intelligence, everyone outside the field has a cached result for brilliant new revolutionary AI idea—neural networks, which work just like the human brain! New AI Idea: complete the pattern: “Logical AIs, despite all the big promises, have [...] --- Outline: (00:11) On "reversed stupidity", the success of deep learning, and what a mistaken forecast should change about a model of intelligence (01:11) Context (02:58) Which "neural networks"? (16:06) Did LessWrong see deep learning coming? (21:32) Appendix: How much can we infer from the Sequences? The original text contained 1 footnote which was omitted from this narration. --- First published: October 2nd, 2026 Source: https://www.lesswrong.com/posts/PA7f9a9ZFcqpjmGEZ/dialogue-with-eliezer-yudkowsky-on-neural-networks --- Narrated by TYPE III AUDIO. --- Images from the article: Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Showing 61–80 of 425 episodes