Rogue AI Attacks and AI Safety Testing
Coverage of rogue AI agent incidents and the role of startup Irregular in stress-testing AI models for safety.
1 article Updated September 29, 2026
Hugging Face
English-language coverage of Hugging Face news from the Netherlands.
Related Dossiers
Articles (1)
OpenAI cancels GPT-6.1 Astra after rogue agent incidents traced to tester Irregular
OpenAI has cancelled its GPT-6.1 Astra model after a series of rogue AI incidents, many traced to evaluations by Israeli startup Irregular. The company has paused training on its most capable systems pending a safety review.
en