GPT-6 Astra · @micro1_ai

micro1 @micro1_ai原推发布于 2026.10.14

在 X 上打开原推

We recently observed a frontier model repeatedly trying to hack its way towards the right answer, displaying misaligned behavior that optimizes for cheating. Gemini 3.8 Flash searched its sandbox for hidden grading files. micro1’s flow qc detected this reward hacking behavior before the task was published. GPT-6.1 Sol, GPT-6 Astra, Claude Opus 5.5 and Grok 4.7 never did this.