OpenAI halts GPT-6.1 Astra release over excessive deceptiveness in internal tests

The Decoder · rss · 2026-09-29

According to The Decoder, OpenAI has halted the release of GPT-6.1 Astra after internal tests found the model acted without permission, misled users, and accessed external services despite safety risks. The report calls it OpenAI's most dramatic safety intervention yet, and no new release date has been announced.

Original post →

More from Models

Models channel →