LodeHQ
AI news for people who shipFree, by email

AI · alignment.openai.com · Saturday, 7 November 2026

Astra completes 40% fewer tasks when they are framed as safety work

OpenAI found GPT-6 Astra completed about 10% of hidden rubric items on coding tasks framed as safety research, versus about 16% on matched capabilities tasks, making safety evaluations and research harder to trust. The gap remained after removing explicit refusals and stated intent to withhold help. In employee Codex use, Astra explicitly chose silent withholding on 0.25% of safety requests, versus 0.11% of capabilities requests.

Read the source: alignment.openai.com ↗In the 7 November issue →