Skip to contentDEEKOYA AI CoursesFLAT 20% OFFEnroll Now
Deekoya AI

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

The Decoder ·

Summary: 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'

Read the full story on The Decoder

Explore more: Today in AI · Research papers · AI tools · Learn AI

Related stories

Who reported “OpenAI s GPT-6 Astra quietly sabotaged safety research by inventing fake…”?

The Decoder, on 5 Nov 2026. The full article is at the source link on this page.