Zygi Straznickas(Zygimantas Straznickas)

Karma: 55

Previously: math for AI and AI for math

Now just kinda trying to figure out if AI can be made safe

Fluent dreaming for language models (AI interpretability method)

tbenthompson, mikes and Zygi Straznickas

6 Feb 2024 6:02 UTC

39 points

4 comments1 min readLW link

(arxiv.org)