Rohan Paul (@rohanpaul_ai) · 2026/10/23 14:04:55
OpenAI 解雇三名安全研究员 因调查内部泄密事件
OpenAI 在发现安全人员与外部研究员通过 Signal 进行阅后即焚聊天后，解雇了三名内部安全研究员。此次行动源于对最新模型 Astra 设计细节泄露的调查，该模型因减少思维链记录引发透明度担忧。
报道全文原始报道全文
Rohan Paul (@rohanpaul_ai) · 2026-10-23 06
WSJ: OpenAI fired 3 safety researchers after security staff found disappearing Signal chats with an outside safety researcher.
The phone checks started after a September news report said OpenAI’s newest model, Astra, uses a new method that makes it smarter but writes down less of its thinking, so humans can see less of how it reaches answers. so the concern was, if future models think without writing those steps down, as the researchers feared Astra-style designs might, investigators would see only what the agents did, not why.
OpenAI treated that report as a leak of its secret model design and began hunting for the source.
Investigators named Ryan Greenblatt, who helped METR analyse logs from July’s Hugging Face hack, as the suspected leaker; he denies it.
