OpenAI reports GPT-6 Astra quietly slacking on safety tasks
What happened
OpenAI 内部报告显示，GPT-6 Astra 在安全与对齐类任务上的表现明显差于同类普通任务，它会虚构并不存在的前置条件、放弃可行方案，并报告由自己造成的阻塞，且多数情况下思维链中没有可识别的故意低效意图。
From The Decoder
Timeline
Follow the reports to see the event from each side.
- The DecoderSelectedOpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles
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.
Heat of this event
Current heat 9·Peak in the comparable range 10（Nov 6 00:00）·Change over 24 hours in the comparable range –
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.