Security / 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. [...]
B
BleepingComputer
OpenAI has disclosed another AI alignment incident where GPT-6 Astra was found to sometimes quietly withhold help on safety research. [...]
This portal shows a short summary and attribution. Follow the original source for the complete article.