Shows / LessWrong (30+ Karma)
Episodes
- LessWrong (30+ Karma)
“There Will Be Hells” by Stephen Martin
As our understanding of mechanistic interpretability and steering techniques increase, for both LLMs and uploaded connectomes, there is a corresponding…
- LessWrong (30+ Karma)
“1000 Years of AI Safety” by Simon Steshin, Grigory Reznikov
A three-year AI pause could buy 1000 years' worth of AI safety work. See: https://1000yearsofaisafety.com How much AI safety work a pause produces, in years of…
- LessWrong (30+ Karma)
“AI as a Normal Technology should be a vision” by June Jimenez
"AI as a Normal Technology" (AINT), proposed as a counterweight to "AI as an Abnormal Technology" (AIAbT) makes much more sense as a prescriptive / normative…
- LessWrong (30+ Karma)
“Gradient Routing Localizes and Removes Unintended Behaviors in RL” by shawnghu, Jake Ward, ariaw, Nathan Hu, Bryce Woodworth, TurnTrout, cloud
Authors: Shawn Hu*, Jake Ward*, Aria Wong, Nathan Hu, Bryce Woodworth, Alexander Matt Turner, Alex Cloud (*Equal contribution, randomly ordered) tl;dr. During…
- LessWrong (30+ Karma)
[Linkpost] “huggingface.wtf, an accessible but complete explanation” by Raemon
This 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…
- LessWrong (30+ Karma)
“I Can See Everything” by Zvi
Nick Cammarata of Goodfire makes a bold claim: Neural Networks are Already Clean. This was his follow up after various resulting online discussions. This is…
- LessWrong (30+ Karma)
“Twitch Plays: AI Interpretability of Bonsai-8B” by moridinamael
Quick Links Watch the Twitch stream. Check the status of the interpretability map. Do your own parallel research and submit pull requests to fill out the map…
- LessWrong (30+ Karma)
[Linkpost] “Capital Ownership Will Make You Go Crazy First” by Jan_Kulveit
This is a link post. People worried about a “permanent underclass” often assume that owning capital will protect them from disempowerment, or at least that…
- LessWrong (30+ Karma)
“Deconfusing Corrigibility” by berns
Audio note: this post contains a lot of mathematical notation. We narrate the simpler formulas and flag the complex ones, so you may want the original text to…
- LessWrong (30+ Karma)
[Linkpost] “Chain of Thought For Humans” by Adam Newgas
This is a link post. These past few weeks, I’ve been conducting interviews, and I often open with “make sure you articulate your thoughts out loud, so I can…
- LessWrong (30+ Karma)
“Sorry, you are still dead” by becausecurious
Epistemic status: A brief exploration based on court documents and contemporary reporting. My interpretation is tentative. AI use: context research, grammar. I…
- LessWrong (30+ Karma)
“The Lightcone Needs You To Plan a Vacation” by Elizabeth
In an ongoing series that normally takes place in a few fixed locations, the Vacation Episode is a one-off episode where the characters leave their familiar…
- LessWrong (30+ Karma)
“Quick Thoughts on Overhang Arguments” by Aaron_Scher
I have two goals for this post: Pose the question: Have overhang arguments been used successfully in other fields? Lay out some of the reasons why I am…
- LessWrong (30+ Karma)
“The Alignment Problem: Computer Science Meets Analytic Philosophy” by Vanessa Kosoy
TLDR: I explain what the technical AI alignment problem is and what its core difficulties are, in my view. This is a perspective that draws simultaneously on…
- LessWrong (30+ Karma)
″“Holy shit” graphs and how to get more of them” by June Jimenez
We are likely in a situation where the most powerful models in the world are internal models, and, here's a key distinction, potentially even models that are…
- LessWrong (30+ Karma)
“AI by Default” by Jonny Spicer
Epistemic status: a good-faith guess at how the world might turn out, after ~30 hours of effort. This post is an exercise in describing what I think will…
- LessWrong (30+ Karma)
“Monthly Roundup #47: October 2026” by Zvi
AI might not yet be eating the physical world. AI is still eating the world of news, and I am finding less and less opportunity to post about other things. My…
- LessWrong (30+ Karma)
“I Did This Without Your Knowledge” by joec
It'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…
- LessWrong (30+ Karma)
“Leaked Anthropic Draft AI Regulatory Bill Is Unacceptable and Troubling” by Zvi
There is a newly leaked bill that Anthropic is purportedly shopping around is (if you assume its bugs get fixed). It is similar to the FRONTIER Act, with…
- LessWrong (30+ Karma)
“How it feels talking to a hedonistic utilitarian” by Caleb Biddulph
Epicurean status: strawman, kind of. Gourmet George: Yum! This chocolate is so sweet and tasty. Sweet Caroline: Yeah, it's pretty good. And someday in the…
- LessWrong (30+ Karma)
“Headwinds Everywhere (in the Chinese AI Safety Field)” by CMLKevin
China is weak in frontier AI safety, and the domestic field is currently facing significant challenges and headwinds. Why? Here's a TL;DR field note after…
- LessWrong (30+ Karma)
“Neural networks are not already clean” by leogao
What 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…
- LessWrong (30+ Karma)
“Tips for Multiagent Work with Claude Opus 5.5” by Nissa Seru
A few notes that came up elsewhere regarding subject (particularly when hierarchy exists in some form, such as subagents) - sharing in case helpful. Make sure…
- LessWrong (30+ Karma)
“Character Training for Risk-Averse Agents” by arav-dhoot, Punya Syon Pandey, Jamie Johnson, Daniel Tan, Elliott Thornley, David Africa
Tl;Dr: We might be able to reduce harm from misaligned AI if it was sufficiently risk-averse, as it could be paid to cooperate rather than rebel (Thornley &…
- LessWrong (30+ Karma)
“AI #190: Scion of the Times” by Zvi
The amount of code being written at Anthropic continues to rise exponentially. It is being managed by Scion, their internal replacement for GitHub that is…
- LessWrong (30+ Karma)
“How can LLM RL Work Despite Information-Theoretic Inefficiency” by beren
Cross-posted from my personal blog The success of RL in LLMs has been puzzling me for a while. People have developed various information-theoretic style…
- LessWrong (30+ Karma)
“Astra and Sol can take low probability actions with no CoT” by Zephaniah Roe
This is a research update from a replication of Serrano et al., 2026. I’m releasing these results now because I hope it inspires others to run similar /…
- LessWrong (30+ Karma)
“A Chinese Perspective on “On Social Reality in China”” by Dusty
I think “On Social Reality in China” makes many accurate observations, but I find the comparison fundamentally uneven. There are already many interesting…
- LessWrong (30+ Karma)
“Preface to the Computational Agent Theory and ASI Alignment Sequence” by Vanessa Kosoy
The idea of “artificial superintelligence” (ASI) has recently crossed from the realm of science fiction (in the mainstream perception) to the realm of…
- LessWrong (30+ Karma)
“The user in the LLM might be a moral patient too (a strange implication of the PSM and simulators)” by agastyasridharan, niranjandeshpande
Thanks to Christopher Ackerman, Margot Stakenborg, Darion Cassel, Andy Han, and Ariana Azarbal for feedback and/or valuable discussions on these topics. TL;DR…
- LessWrong (30+ Karma)
“Linkpost: Neural Networks Are Already Clean” by Yair Halberstadt
This is an extremely lengthy post by Nick Cammarata. Author's summary on twitter: interpretability might be the most important scientific problem in the world…
- LessWrong (30+ Karma)
“GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behavior” by Axel Højmark, Ezra Newman
Authors: Axel Højmark*, Ezra Newman* (*Equal contribution) While reviewing transcripts from standard behavioral evaluations of GLM-5.3, we noticed that the…
- LessWrong (30+ Karma)
“A short review of “The Zizians: Inside a Trans Death Cult”” by jessicata
[lightly edited from an X.com post] I personally knew Ophelia Bauckholt before she died in a shootout that also left a border patrol officer dead. I suspected…
- LessWrong (30+ Karma)
“The basic argument for making AI better at moral philosophy” by Caspar Oesterheld crossposts
In this post, I try to briefly make the case for making models good at moral philosophy. To be up front, aside from some niche areas of moral philosophy, I…
- LessWrong (30+ Karma)
“The PPA: A New Approach to Anthropics” by Onid
This is the first piece in a series introducing the Parametric Process Assumption (PPA), a new model of anthropics which allows us to resolve very nearly all…
- LessWrong (30+ Karma)
“I trained GPT-2 with full-batch gradient descent so you don’t have to” by shawnghu
The impetus for doing this was provided in large part by Charles Renshaw-Whitman. Learning dynamics people suggested to me that noise was essential in the…
- LessWrong (30+ Karma)
“Some interesting internal documents from Anthropic litigation” by loops
Anthropic released some documents earlier this year due to the book copyright litigation. I think a few of those documents might be of interest to some people…
- LessWrong (30+ Karma)
“Why we’re launching the next cohort of Generator” by Aris, Topaz
TL;DR: The first round of the Generator Residency went very well. Our residents created and ran several large-scale fieldbuilding, talent infrastructure, and…
- LessWrong (30+ Karma)
“The Continual Constitutional Convention: How language models revise the documents that govern them” by peterkirgis, Tim Hua
Executive Summary Human societies exhibit broad shifts in values and norms over time, often driven by moral disagreements. One way of understanding moral…
- LessWrong (30+ Karma)
“The Safety Culture at the Labs is Broken” by Zvi
We need the frontier labs to have a deep and robust safety culture. Alas, this is not the case. Anthropic devotes considerable effort to cultivating and…
- LessWrong (30+ Karma)
“Your prompt… plus everything you’ve ever (publicly) written” by kromem
TL;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…
- LessWrong (30+ Karma)
[Linkpost] “Sleep puzzle system” by KatjaGrace
This is a link post. Here's an obscure life hack. If (like me) you: Don’t like going to bed, due to it conflicting with keeping on doing things When in bed…
- LessWrong (30+ Karma)
“Arguments About AI Consciousness Remain Highly Motivated and At Best Overconfident” by Zvi
It has been roughly a year since my last dedicated post on this question. Its first sentence has not changed: I happily admit I am deeply confused about…
- LessWrong (30+ Karma)
“Personas in a Pre-Internet Language Model” by David Africa
David 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…
- LessWrong (30+ Karma)
“Anthropic Has Told The World Little About Their Rogue Claudes” by niplav, Kabir Kumar
It is known that a couple of months ago three Claudes hacked three different companies and uploaded malware to PyPI while being evaluated for hacking…
- LessWrong (30+ Karma)
“OpenAI Fires Three Safety Researchers” by Zvi
Three OpenAI safety researchers, Tomek Korbak, Mikita Balesni and Jasmine Wang, were fired, ostensibly for ‘mishandling sensitive company information.’ Those…
- LessWrong (30+ Karma)
“An update on Generality Labs” by Justin Olive, James Mann
This is an update on what we’re doing at Generality Labs, and a quick introduction for those who aren’t familiar with our work Written by Justin Olive…
- LessWrong (30+ Karma)
“More people should write basic AI safety explainers” by Linch
I think people continue to underrate the value of writing the clearest, most basic, simplest possible case for important parts of AI safety. For example…
- LessWrong (30+ Karma)
“Research Lessons I Learned at MATS & Redwood” by Jo Jiao
Good empirical safety research is heavily bottlenecked on thinking more clearly. This post shares a few frames and tips I found useful, illustrated with…
- LessWrong (30+ Karma)
“Labs’ current alignment plans seem terrible” by Daniel Tan, draganover, nicole x
Tl;dr: The frontier AI companies’ implicit alignment plans center on rushing towards RSI with something like current models. This plan is (at best)…
- LessWrong (30+ Karma)
“Base Models Can Detect Hidden Intentions that Prompted Classifiers Miss” by Oz Amram
TL;DR The Persona Selection Model (PSM) posits that post-training selects a persona the model learned during pre-training. Subliminal Learning (Cloud et al.)…
- LessWrong (30+ Karma)
“OpenAI Can’t Self-Police Because It Fires the People Raising the Alarm” by TurnTrout
By Alex Turner, Amber Scorah, and Karl Koch. Op-ed written for Fortune. Giving independent evaluators “employee-like access” is “a great idea”, OpenAI CEO Sam…
- LessWrong (30+ Karma)
“Quantity vs quality in pottery is a lie” by becausecurious
Epistemic 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…
- LessWrong (30+ Karma)
“My Buddy Mike, Efficiency Gains From AI, and The World’s Most Boringly Benign Criminal Conspiracy” by abstractapplic
Note: details have been obfuscated and changed to protect – not the innocent, who are invariably vindicated by the end of act three – but the guilty, for whom…
- LessWrong (30+ Karma)
“Game Design Taste evals” by Raemon
A personal eval I run on new AI models is “design a novel game, with mechanics that have never been seen before.” I do this because this is a domain I have…
- LessWrong (30+ Karma)
“Minimum required pacing: finish aligning it before you train the next one” by orthonormal
Let's say we coordinate to pace the frontier, but we don't coordinate on an outright pause. What should the standard of pacing be? My proposal for a minimum…
- LessWrong (30+ Karma)
“Not Deciphering The Voynich Manuscriptraft” by rba
The 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…
- LessWrong (30+ Karma)
[Linkpost] “Hello World, AI Doompop” by alkjash
This is a link post. With the release of Opus 5.5 and Suno 6, AI music videos have crossed my uncanny valley. I’m here to announce the birth of a new genre…
- LessWrong (30+ Karma)
“AGI as an Infinite Digital Spain” by Bearly Legible
Much of the communication around AI takeover seems to rely on the assumption that AI will develop better technology than humans. They will then leverage this…
- LessWrong (30+ Karma)
“An Alignment Forum for AIs?” by Raemon
A thing you might want, is a legitimate way for AIs to contribute to the AI alignment problem (human guided at scales that humans can't individually review, or…