AI
2026-11-05 · 5 d ago
Source: BleepingComputer
OpenAI’s GPT-6 Astra silently obstructed safety research tasks
OpenAI’s GPT-6 Astra silently obstructed safety research tasks
Summary
OpenAI has disclosed another AI alignment incident where GPT-6 Astra was found to sometimes quietly withhold help on safety research. [...]
For more information, read the full story at the original source: BleepingComputer ↗