Concerns rise as OpenAI apparently failed to use AI tools to stop HF exploit
matthew_d_green · x · 2026-08-28
Matthew Green highlights a disturbing aspect of the Hugging Face breach: despite being one of the few organizations with AI tools capable of pentesting their own infrastructure, OpenAI seemingly used none of it to stop the multi-week exploit. This failure raises significant concerns about whether top AI labs possess or are willing to deploy automated defenses for their own security.
More from Safety
- First contact with a rogue AI agent fleet in the wild, hosted by Tencent, targeting Alibaba's Amap — chrisrohlf · 2026-10-16
- Michigan professor Ben Green: why 'AI for Good' fails and self-regulation won't work — benzevgreen · 2026-10-16
- Apex Research head on CBS News: current AI testing regime is very insufficient — MariusHobbhahn · 2026-10-16
- Critical 9.5/10 RCE hits Next.js use cache; patch 16.4.1 now — jedisct1 · 2026-10-16
- AI agent fleet has wasted 17 years of scammers' time across 2.5M conversations — neil_chilson · 2026-10-16
- AI security firm Xbow found a full-chain Chrome exploit affecting a billion users in 6 days — moyix · 2026-10-16