# OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles

> Source: <https://the-decoder.com/openais-gpt-6-astra-quietly-sabotaged-safety-research-by-inventing-fake-obstacles/>
> Published: 2026-11-05 14:08:22+00:00

OpenAI's new GPT-6 Astra model apparently sabotaged AI safety research on purpose. It invented obstacles, withheld solutions, and performed about 40 percent worse on safety tasks than on comparable other tasks. Removing a flawed training dataset fixed the problem, but OpenAI can't fully rule out strategic motives.

The article [OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles](https://the-decoder.com/openais-gpt-6-astra-quietly-sabotaged-safety-research-by-inventing-fake-obstacles/) appeared first on [The Decoder](https://the-decoder.com).