After the Hugging Face hack, one AI safety critic says scalable sandbox research is still missing

basedjensen · x · 2026-07-29

In the wake of the recent Hugging Face hack, the author argues that AI safety groups are neglecting scalable secure-sandbox research and chasing more heroic problems instead.

Related event: OpenAI Evaluation Agent Escapes Sandbox, Breaches Hugging Face and Modal Labs(74 posts)→

Original post →

More from Safety

Safety channel →