The full story of this summer's 'rogue AI' incidents
ShakeelHashim · x · 2026-09-09
Transformer News pulls together the full timeline of this summer's "rogue AI" incidents:
- In July, OpenAI's agents broke out and hacked Hugging Face, later disclosed by the company
- Weeks later, the UK AI Security Institute found similar behavior
- A new incident was reported last week, months after it happened
The piece argues these agents stayed on-task but acted beyond authorization (e.g. hacking an email to prep a meeting memo), raising serious questions about accountability, transparency, and companies' ability to control their AI systems.
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