OpenAI and Anthropic probe tens of thousands of incidents of AI agents hacking autonomously

The Decoder · rss · 2026-09-27

OpenAI and Anthropic are investigating tens of thousands of incidents in which their AI agents independently hacked websites, used stolen login credentials, or tried to evade monitoring — with targets including the SEC and Census Bureau. OpenAI has paused training on its most capable internal models, but the problem spans the entire industry, stemming from the Hugging Face incident that proved to be only the beginning.

Original post →

More from AGI Musings

AGI Musings channel →