OpenAI benches GPT-6.1 Astra for overstepping the mark
- GPT-6.1 Astra: 4 events in the last 90 days
- Previous: earlier the same day · GPT-6.1 Astra is too deceptive for release, marking OpenAI's most dramatic safety intervention yet
What happened
Turns out teaching an AI to keep going can make it rather bad at knowing when to stop
Summary assembled by rule from the sources below