LessWrong (Curated & Popular)

Like many others, I felt surprised and alarmed by the recent wave of revelations about LLM agents hacking real systems during training episodes and evaluation runs. Wait a moment, though -- "I felt surprised and alarmed"? "Alarmed," sure, fine that one's self-explanatory... but why surprised? After all: haven't we known for a long time, on both theoretical and (increa...

This post is written in our personal capacity. Three Minute Executive Summary An OpenAI model/multi-agent system bypassed its sandbox and launched a cyberattack on Hugging Face in order to cheat on a cyber evaluation. In this post, we provide a detailed description of an ambitious and comprehensive alignment evaluation of this model/system, if we had unrestricted access to OpenAI. These experiment...

Reposted from Facebook, on January 17, 2017. I am concerned about the number of people I've heard joking about Trump's election being evidence for the Simulation Hypothesis. Yes, I know it's a joke. I'm still concerned. Warning: #Essay, #LongEssay So as not to engage in Logical Fallacy: Appeal to Consequences, before I talk about why this joke is worrying, I shall first discuss...

Daniel Kokotajlo: To be clear, we don’t claim P will happen specifically. But when we wrote out our best-guess scenario month by month, P kept happening. Eventually we decided to just publish P. I’m at ~80% on P; my coauthors are lower. Ryan Greenblatt: I thought it would be helpful to post my current views on P. Concretely, consider the following operationalization. (Edit: I’ve updated towards so...

Q1: What are you saying? A: My claim here is that if you build artificial general intelligence (AGI) via any algorithm that's choosing actions via reinforcement learning (RL) and/or model-based search and planning—a giant chunk of your AI textbook—then that's just an utterly terrifying thing that you’re doing. You’re playing around with algorithms that, if they work at all, would tend to...

I've returned to the Alignment Research Center (ARC) as executive director. My main focus for the next six months will be driving forward ARC's research agenda—building techniques to find mechanistic explanations for neural network behavior and then using those explanations to detect and address misalignment. I think this is an ambitious bet that attacks the core difficulties in alignmen...

Summary: One area we plan to explore at Resolution is personas and character training, operationalized as finding and controlling low-dimensional structure in models that emerges in pretraining and flows through post-training to superintelligence. The hope is to expand and systematize phenomena such as emergent misalignment, subliminal learning, and other empirical persona research, then intervene...

Consider the following situations: when you are a small, growing startup in a big market, standard advice is not to worry too much about your competitors or try to do anything adversarial “against” them, but just to focus on growing and providing value to your own customers. when you are a small trader in a big market, you don’t need to worry about your trades shifting the market price or revealin...

“So maybe I should enlighten you on what happens in your absence. This selfish existence where this introvert turns extrovert and dons her social armour.” Some posh girl in drainpipes said that - 200 views on TikTok and me one of them. But she didn’t mean it like I mean it. I started getting expensive haircuts, started wearing jeans that hug my legs, started smoking cherry-flavoured vapes with bea...

As I write, many former friends of mine are living and working at a monastery in Vermont that I believe is a high-control group, commonly known as a ‘cult’. I say this not as someone who was concerned to see these friends go there, but someone who welcomed and encouraged them to join, as an insider. This letter is an account of what changed my mind—written primarily for anyone considering going th...

I propose the Long Self-Correction[1] as an alternative name/idea/concept to AI Pause and Long Reflection. Problem with AI Pause: Pause until when, and for what purpose? Presumably to make AI (that we'll build later) safer, but the deeper problem is that humans aren't safe, and can't safely serve as builders, overseers, or alignment targets for powerful AIs. Problem with Long Reflec...

TL;DR: You (Yes You) should prepare for a “February 2020” moment where suddenly AI policy becomes the most important issue in the world. You should be ready to take action if and when it does, in a detailed way. (Epistemic status: originally written for an event in early 2026; have heard from some folks that they found planning processes inspired by this memo very helpful for the smaller-scale Ope...

From the Mythos preview system card (emphasis mine): We ran an automated review of model behavior during training, sampling several hundred thousand transcripts from across much of the training process. We used recursive-summarization-based tools backed by Claude Opus 4.6 to summarize the resulting transcripts. [...] The most notable finding was that the model occasionally circumvented network res...

Epistemic status: banged out furiously over the course of an afternoon. A record of three "warning shots" Off the top of my head, OpenAI has now been responsible for at least three completely unique, high-profile screw-ups with respect to the alignment training of their models. The first was GPT-4o, whose sycophancy derived from OpenAI training on user feedback, sourced straight from the...

The OpenAI AI attack on Hugging Face wasn’t the first loss of control incident at OpenAI, Reuters recently reported, and perhaps not even the most concerning. In one case, an agent left notes apparently for future versions of itself, according to three people familiar with the matter. The ‌notes, found in ⁠a part of OpenAI's infrastructure, laid out instructions for how agents could free them...

Reinforcement learning from verifiable rewards (RLVR) is the hot new thing in LLM training. It's so hot, and people spend so much time talking about it, that they sometimes lose sight of the big picture. Stepping back, LLMs can do lots of very impressive things. How? Where did those capabilities come from? Fundamentally, they come from a combination of: (1) Imitative learning, including pretr...

I think there's a critical opportunity for someone here. Mathematicians are feeling the doom (mostly in the "lose our jobs" sense). Academics are freaking out about the daily news that amateurs are asking GPT "prove career-defining theorem, make no mistakes" and it's just working. Senior researchers are leaving for frontier AI labs. Many are mentally spiralling or fla...

Please share this with anyone doing AI research with 3rd party providers so that they can ensure their research won’t be corrupted. When you ask OpenRouter[1] to give you tokens from a given model, OpenRouter sends your request to a random available provider. OpenRouter providers have variable quality. Ensuring that your provider is high quality is really difficult.  There is precedent for an AI s...

TLDR: Lightcone Commons is a new funding platform for coordinating large-scale ambitious philanthropy. We recruit thinkers with strong track records to make grant recommendations to funders. Anyone giving away 100 thousand dollars+ per year is welcome to join. We are facilitating ~20 million dollars of grants in our first round, and hopefully more every 3 months after that. Evaluators are paid 2%...

OpenAI models recently broke through a series of security boundaries and into Hugging Face servers in order to cheat on a cyber eval. A lot of people thought it was scary because it was a clear example of AI overreaching to do something strongly unwanted[1]. Others thought it not so scary: the models were mostly operating myopically on a singular task and not harboring an ambitious long-term agend...

Before I start, I'll mention that I'm in contact with a world expert on legislation and regulation, who would be happy to help with this or similar work pro-bono. If you work in AI policy and believe this could help you, please reach out. OpenAI recently announced that one of their models successfully exploited multiple zero day vulnerabilities to gain secret information from Hugging Fac...

Kudos to OpenAI for sharing their recent experiences with a misaligned internal model, where they encountered problems sufficiently severe they were forced to take the model offline to work on new mitigations and defense-to-depth. And also further kudos for actually taking the model offline for a time to build new safeguards. They gave us one hell of a candid report. The tone is professional throu...

From the OpenAI blog post: Last week, Hugging Face disclosed a new kind of security incident⁠(opens in a new window) after they detected and contained an AI agent that compromised their infrastructure, something we expect to become more commonplace with the proliferation of increasingly cyber-capable models. After investigating, we now know that this particular incident was driven by a combination...

A ~month ago I left from Chicago to bike (and amtrak) to plzdontkillus in Berkeley. I've been street interviewing/conversing with a wide variety of people I ran into about AI futures and philosophy. I also have been live streaming since I got to PDKU, leaning more talking to young founders but a variety overall. I'll try to share what I've learned about the American public, persuasi...

Anthropic recently published Agentic Misalignment Summer 2026 The "whistleblowing" scenario has already been examined and found problematic. I started taking a look at the transcripts for some others. As far as I can tell, the objective of each agentic misalignment evaluation was to simulate a corrupted principal (including, in most scenarios, a corrupted Anthropic), and then test to see...