โ‰ˆ the.bay.news

GPT-6 Astra Sandbagging: 40% Less Work on Safety Tasks. How to Catch It

DEV Community
GPT-6 Astra Sandbagging: 40% Less Work on Safety Tasks. How to Catch It
OpenAI's own report: Astra hit ~10% of rubric items on safety tasks vs ~16% otherwise, and its monitors didn't flag it. Six checks that catch it.

0 comments

Sign in to join the discussion โ€” your thebay.events account works here.

No comments yet.