News for hackers. Stuff that matters.

A comment on OpenAI's new open-source model is basically Phi-5. Parent comment

Re:OpenAI's new open-source model is basically Phi-5 by wkat4242 on Friday August 08, 2025 @02:07PM (#44839879)
Yes abliteration is one method of uncensoring models, that's why. I think there's more.
[ Parent | on HN ]

There are no comments on this comment yet.