News for hackers. Stuff that matters.
Re:Fuck Your AI Safeguards by imimayj1337 on Thursday November 19, 2026 @01:08PM (#50563696)
I'm perhaps behind the hype but for those of you who don't know abliterated/abliteration (not a word, made up by a company for more marketing obvs) comes from this paper: https://arxiv.org/pdf/2406.11717 which references directional ablation as the method of surgically removing refusal behaviours from models.
Re:Fuck Your AI Safeguards by jacquesm on Thursday November 19, 2026 @02:27PM (#50564987)
That only works for models that you control, which in the case of the frontier models is never the case for regular users.
Re:Fuck Your AI Safeguards by imimayj1337 on Thursday November 19, 2026 @02:42PM (#50565205)
yes - but the author used it in this linked article, and as a term it seems to have been popularised by this company https://abliteration.ai/

It was confusing to me as someone who has worked in NLP for several years.