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
Interpreting neural networks through the polytope lens (2022)(lesswrong.com)76 points by sva_ 2 years ago | 6 comments
Significantly Enhancing Adult Intelligence with Gene Editing May Be Possible(lesswrong.com)12 points by vwoolf 2 years ago | 2 comments
How much are LLMs boosting real-world programmer productivity?(lesswrong.com)55 points by gatinsama 1 year ago | 61 comments
AIs Will Increasingly Attempt Shenanigans(lesswrong.com)19 points by surprisetalk 1 year ago | 12 comments
