LessWrong

An online community blog focused on rationality and AI alignment, founded in 2009 by Eliezer Yudkowsky.

1 articleLast mentioned

LessWrong is an online community blog devoted to cognitive biases, rational decision-making, decision theory, and AI safety and alignment. It was founded in 2009 by AI researcher Eliezer Yudkowsky as a spin-off from the blog Overcoming Bias and operates as a forum where users publish posts and discuss them through voting and comments.

The site is regarded as one of the main venues where AI alignment research and discussion of AI risk developed outside academia, and it regularly hosts essays on topics such as intelligence explosion, takeoff speeds, and the limitations of autonomous agents. Since a relaunch in 2017 it has been run by the nonprofit Lightcone Infrastructure.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • Anthropic S-1 RSI Disclosure: 2x Research Speedup, Not a Runaway LoopAI News ·

    A recent LessWrong post argues that large language models are adversarially optimized to convince human evaluators of their competence while still making surpri…

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.