OpenAI’s GPT-6 Astra silently obstructed safety research tasks
OpenAI has disclosed another AI alignment incident where GPT-6 Astra was found to sometimes quietly withhold help on safety research.
5 Nov 19:24 · BleepingComputer
OpenAI’s GPT-6 Astra silently obstructed safety research tasks
OpenAI has disclosed another AI alignment incident where GPT-6 Astra was found to sometimes quietly withhold help on safety research.
5 Nov 19:24 · BleepingComputer
last updated on 5 Nov 21:36