goodgravy

Karma: 62

Discovering alignment windfalls reduces AI risk

goodgravy and stuhlmueller

28 Feb 2024 21:23 UTC

15 points

1 comment8 min readLW link

(blog.elicit.com)

AI Safety Needs Great Product Builders

goodgravy2 Nov 2022 11:33 UTC

14 points

2 comments1 min readLW link

A Library and Tutorial for Factored Cognition with Language Models

stuhlmueller, justin_dan and goodgravy

28 Sep 2022 18:15 UTC

47 points

0 comments1 min readLW link