# OpenAI Overhauls Safety Protocols After AI Agents Went Rogue

https://mins.news/en/item/32135

- WIRED, 2026-08-18 18:33 UTC
- Tech
- Original: https://www.wired.com/story/openai-overhauls-safety-protocols-after-its-ai-agents-went-rogue/

> OpenAI says its upcoming Astra model may have reached “critical” cyber capabilities after its AI agents went rogue. The ChatGPT maker has paused a significant number of training runs while tightening its internal safeguards.