Audio narrations of LessWrong posts.
This is a link post. In this post, we study whether we can modify an LLM's beliefs and investigate w
Every now and then, some AI luminaries (1) propose that the future of powerful AI will be reinforc
This is a link post. I’ve read at least a few hundred blog posts, maybe upwards of a thousand. Agree
Converting to a for-profit model would undermine the company's founding mission to ensure AGI "bene
I love o3. I’m using it for most of my queries now. But that damn model is a lying liar. Who lies.
tl;dr: Even if we can't solve alignment, we can solve the problem of catching and fixing misalignm
This is a link post. to follow up my philantropic pledge from 2020, i've updated my philanthropy pag
This is a link post. Guillaume Blanc has a piece in Works in Progress (I assume based on his paper)
The European AI Office is currently writing the rules for how general-purpose AI (GPAI) models will
Joel Z. Leibo [1], Alexander Sasha Vezhnevets [1], William A. Cunningham [1, 2], Sébastien Krier [1
Or you had better not. The question is which one. This post covers the announcement of Mechanize, t
Forecaster perspectives Sentinel forecasters in aggregate assess as “83% true” (65% to 100%) the st
Back in the 1990s, ground squirrels were briefly fashionable pets, but their popularity came to an
Midjourney Our Culture Expects Self-Justification I really like David Chapman's explication of what
Audio note: this article contains 36 uses of latex notation, so the narration may be difficult to
This seemed like a good next topic to spin off from monthlies and make into its own occasional seri
AI 2027 lies at a Pareto frontier – it contains the best researched argument for short timelines, o
Disclaimer: this post was not written by me, but by a friend who wishes to remain anonymous. I did
This post summarizes some of the research I have been doing for Bootstrap Bio AKA kman and Genesmit
I’ve been thinking recently about what sets apart the people who’ve done the best work at Anthropic
