Can large language models reason?(arnaldur.be)

4 points by Hugsun 2 years ago | 0 comments

Douglas Hofstadter changes his mind on Deep Learning and AI risk(lesswrong.com)

216 points by kfarr 3 years ago | 305 comments

Alignment faking in large language models(lesswrong.com)

29 points by surprisetalk 1 year ago | 4 comments

Do large language models need all those layers?(amazon.science)

155 points by belter 2 years ago | 72 comments

Recent AI model progress feels mostly like bullshit(lesswrong.com)

474 points by paulpauper 1 year ago | 375 comments

LessWrong linkpost essay arguing recent AI model improvements feel overstated, based on experience building an AI codebase security-scanning startup.

Mechanistic interpretability researchers applying causality theory to LLMs(cacm.acm.org)

95 points by adunk 3 months ago | 68 comments