←back to thread

Uncensor any LLM with abliteration

(huggingface.co)
586 points mizzao | 1 comments | 13 Jun 24 03:42 UTC | HN request time: 0.206s | source
Show context
joe_the_user ◴[13 Jun 24 04:45 UTC] No.40666038[source]▶
So this seems to be about uncensoring a model that the user is running locally. Is that right, do they expect to limit what someone can do under those circumstances? Kind of like expecting no one to break local copy protection, except copy protection with much less reliable tools.
replies(2): >>40666271 #>>40666425 #
1. Mathnerd314 ◴[13 Jun 24 05:32 UTC] No.40666271[source]▶
There are many hacks to uncensor LLMs, the surprising thing is that this is fairly simple but works really well.