(github.com)

745 points melded | 1 comments | 16 Nov 25 15:00 UTC | HN request time: 0.319s | source

1. krackers ◴[17 Nov 25 01:23 UTC] No.45950075[source]▶

https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in... provides more detailed information on the theory behind abliteration

Heretic: Automatic censorship removal for language models