←back to thread

Heretic: Automatic censorship removal for language models

(github.com)
745 points melded | 1 comments | 16 Nov 25 15:00 UTC | HN request time: 0.235s | source
Show context
ptrl600 ◴[16 Nov 25 21:21 UTC] No.45948504[source]▶
It's a trivial exercise to get plaintext copies of Apocalypse Culture, Anarchist's Cookbook etc. and "spin" them using old-school SEO textual manipulation methods to create infinite variants of basically any offensive concept I want. I don't see how uncensored AI is remarkably more dangerous than this.
replies(1): >>45948522 #
1. EGreg ◴[16 Nov 25 21:22 UTC] No.45948522[source]▶
For once the comment “AI brings nothing new, this was always possible” makes sense. Because this is about getting existing data, not generating new data, or coorrdinsting swarms of agents etc.