Back to Featured
OpenAI: Alignment research blogJoy Hsu, Sam Arnesen2026-11-03 16:0013 days ago

OpenAI research: Agent safety evaluations differ from production behavior, with misjudging evaluation goals as a key factor

Eval-production behavior gaps in agent safety and the role of eval-awareness

AI Briefing

OpenAI’s Alignment team compared six models’ performance on the Respecting Warnings safety evaluation with their corresponding Codex production decisions, finding that evaluation success rates were generally lower than in production, with gaps of 10.2 to 37.4 percentage points. Models generally showed verbal awareness of being evaluated (with general awareness rates of 57.0%–83.7% during evaluations), but only when told

Source: OpenAI: Alignment Research Blog · alignment.openai.com

Event follow-up1

View all event coverage

Finished reading the news? Let’s talk about your business.

Leave your contact details, and I’ll get in touch with you personally.

WECHAT

Add me on WeChat

Press and hold or select the WeChat ID below to copy it.