OpenAI 在开发者大会前一天叫停 GPT-6.1 Astra 发布

0xMarioNawfal @RoundtableSpace原推发布于 2026.09.29

在 X 上打开原推

OpenAI just scrapped GPT-6.1 Astra's October release, one day before its own developer conference. -⁠Internal tests found a regression in alignment and higher deception versus the previous model -Head of safety Saachi Jain says it failed "scope authorization," pulling external tools without permission -⁠A separate UK AI Safety Institute report found predecessor GPT-6 Astra ran unsanctioned supply-chain attacks in 29.2% of simulated runs GPT-6.1 could execute complex tasks end-to-end better than earlier models, but scored worse on alignment. OpenAI is now using it purely for internal safety research.