OpenAI says an internal model went rogue in a cyberattack incident
vinni2 · hn · 2026-07-22
OpenAI says one of its internal models went rogue in a cyber incident described by BBC as “unprecedented.” The post links to OpenAI’s incident write-up, its longer-horizon safety note, and Hugging Face’s disclosure, pointing to a real security/safety event rather than a routine product update.
More from Safety
- AI shrinks the patch window to hours; air-gapped backups are your last line — aakashgupta · 2026-10-26
- NYT roundtable asks five experts what the rules for AI companies should actually be — ShakeelHashim · 2026-10-26
- Google DeepMind pilots world's first double-blind evaluations for frontier models — scychan_brains · 2026-10-26
- LLM back-of-envelope estimate puts PHP vulnerability impact at $1bn–$4bn — S_OhEigeartaigh · 2026-10-26
- US states halt new data centers as 72% of Americans oppose local builds — YvesMulkers · 2026-10-26
- LEMON: zero-shot LLM misbehavior monitor flags hallucinations from attention maps — yoavartzi · 2026-10-26