Audio narrations of LessWrong posts.
I frequently hear people make the claim that progress in theoretically physics is stalled, partly b
I quote the abstract, 10-page "extended abstract," and table of contents. See link above for the fu
We show that LLM-agents exhibit human-style deception naturally in "Among Us". We introduce Decepti
Right now, alignment seems easy – but that's because models spill the beans when they are misaligne
Summary: Meditation may decrease sleep need, and large amounts of meditation may decrease sleep nee
A new Anthropic paper reports that reasoning model chain of thought (CoT) is often unfaithful. They
Summary: When stateless LLMs are given memories they will accumulate new beliefs and behaviors, and
Epistemic status – thrown together quickly. This is my best-guess, but could easily imagine changin
Yeah. That happened yesterday. This is real life. I know we have to ensure no one notices Gemin
Hello, this is my first post here. I was told by a friend that I should post here. This is from a s
“In the loveliest town of all, where the houses were white and high and the elms trees were green a
We are pleased to announce ILIAD2: ODYSSEY—a 5-day conference bringing together 100+ researchers to
In 2021 I wrote what became my most popular blog post: What 2026 Looks Like. I intended to keep wri
Greetings from Costa Rica! The image fun continues. We Are Going to Need A Bigger Compute Budge
Intro [you can skip this section if you don’t need context and just want to know how I could believ
Epistemic status: This should be considered an interim research note. Feedback is appreciated. In
A key step in the classic argument for AI doom is instrumental convergence: the idea that agents wi
Let's cut through the comforting narratives and examine a common behavioral pattern with a sharper
Recent progress in AI has led to rapid saturation of most capability benchmarks - MMLU, RE-Bench, e
In the debate over AI development, two movements stand as opposites: PauseAI calls for slowing down