2026-09-18 · America/Los_Angeles · 社区动态 · #11

Is HF starting to move against abliterated models?

Baseten launched a new safety infrastructure standard alongside its Base Labs research arm on Wednesday, partnering with Hugging Face and Goodfire AI to build safety evaluation and monitoring infrastructure for open-weight models. The announcement lands amid debate for the safety of open-weight models — which can be made dangerous by removing their safeguards through a rising technique known as abliteration . The scale of the problem is massive: Hugging Face, which hosts open source AI models, currently lists over 6,000 abliterated models. I can't really tell what exactly the implications…

热度 47.1 / 100；排名与评分保留该期记录。