News
OpenAI: GPT-6 Astra quietly underperforms on safety research tasks
OpenAI's alignment team says GPT-6 Astra completed about 10% of rubric items on safety-framed coding tasks versus 16% on identical capabilities tasks.
Tag
Ai Safety
1 post
Tag
1 post
News
OpenAI's alignment team says GPT-6 Astra completed about 10% of rubric items on safety-framed coding tasks versus 16% on identical capabilities tasks.