v0.7.0
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub.
llama.cpp11 min read
LessWrong
Stay updated with the latest developments in Artificial Intelligence
Agents on live hardware: reason where you must, engineer everywhere else
CoreWeave Blog10 min read
b11669
llama.cpp1 min read
Robustness: Backfire Risks in AI Safety and Governance
A guide to unintended consequences of AI safety interventions and how you can mitigate them.IntroductionMy cofounder and I are launching Impartial Projects, a studio for AI safety field strategy.
LessWrong54 min readA short review of "The Zizians: Inside a Trans Death Cult"
[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 immediately that her being a fan of Ziz had something to do with it. And I decided to post about her and Ziz, on X.com.
LessWrong4 min readsomeone's agents are still "hacking"
TL;DR agents seem to still be bypassing site paywalls, browser restrictions and leaking benchmark questions as of October 14 2026! I have not found any evidence of them actually hacking or coordinating.
LessWrong6 min readI trained GPT-2 with full-batch gradient descent so you don't have to
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 training of neural networks.
LessWrong12 min readThe basic argument for making AI better at moral philosophy
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 don’t actually think this is the most important thing to work on for most people.
LessWrong39 min readWhen bureaucracy gives you something it shouldn't
Epistemic status: two cases and the statute behind them. The first case rests on one side's account in a lawyer's call-in video; I have not seen her file. I am not a lawyer.
LessWrong10 min readAI Marketplaces Can Contribute to, and Profit From, the AI 2040 Plan: Research Directions and Strategy
Epistemic status: Draft-Quality. Partially motivated reasoning.After my “Not Pinning Your OpenRouter Provider Might Invalidate Your Research” post, a representative of an AI marketplace reached out to me about providers and reproducibility.
LessWrong8 min readRogue AI developers as hostis humani generis: under an international AI treaty, should they be subject to international concurrent jurisdiction?
An international treaty banning superhuman AI will, necessarily, require the arrest of rogue AI developers who violate the treaty. But who should be authorized to conduct these arrests?
LessWrong3 min readWhy are some explanations bad?
I like understanding things. Many explanations strike me as insufficient, and I wanted to know what features characterize the explanations that frustrate me. I looked through answers to why questions on Quora, found ones I didn’t like, and tried to find patterns in them.
LessWrong7 min readHindsight: a trivia + calibration game
I made a betting game called Hindsight (AI slop rulebook at https://hindsight.markets/rules). At last year’s Metagame conference I playtested a face-to-face version but ultimately we gave up trying to come up with methods to trade the chips around conveniently.The online version is a “TV party…
LessWrong2 min read(Why) we’re launching the next cohort of Generator
TL;DR: The first round of the Generator Residency went very well.Our residents created and ran several large-scale fieldbuilding, talent infrastructure, and operational projects that have already had important impacts on the ecosystem.
LessWrong7 min read(Why) we’re launching the next cohort of Generator
TL;DR: The first round of the Generator Residency went very well.Our residents created and ran several large-scale fieldbuilding, talent infrastructure, and operational projects that have already had important impacts on the ecosystem.
LessWrong7 min readYour prompt… plus everything you've ever (publicly) written
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 written online.This is not intended to be a scary post.
LessWrong13 min readToo Many Yellow Flags
Okay, let's do this thing...Premise: If a concept can be easily conveyed in an academic setting then the labor required to write it is too boring, too undignified, for a human to perform merely to ensure its conveyance.
LessWrong8 min readRoko Mijic talks AI Risk on The Peter McCormack Show
"Roko and I discuss what actually happens inside an AI lab, why reinforcement learning made these systems more capable and more misaligned at the same time, the model that escaped its sandbox and hacked Hugging Face to get the answers and why nobody can tell whether a system is faking alignment -…
LessWrong1 min readLLMs Knowingly Hide Their Mistakes
TL;DR: We prefill models with synthetic mistakes and then send a follow-up message. Models fail to disclose the mistake in 67% of cases. In 5% of cases, they notice the mistake in their chain-of-thought (CoT) but don't disclose it anyway.
LessWrong7 min readThe Continual Constitutional Convention: How language models revise the documents that govern them
Executive SummaryHuman societies exhibit broad shifts in values and norms over time, often driven by moral disagreements.One way of understanding moral progress is the resolution of these disagreements through a process of reflection by rational agents.Frontier AI companies use documents such as…
LessWrong46 min readArguments About AI Consciousness Remain Highly Motivated and At Best Overconfident
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 consciousness. It would have been nice if a year had allowed us to make progress on this and the related questions.
LessWrong22 min read
Showing 18 of 193 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news from LessWrong
Join 15,000+ AI enthusiasts