TechOpenAI Overhauls Safety Protocols After 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.

OpenAIAstraAI safety

WWIRED★★★☆☆2026-08-18 18:33Original