WSJ 称 OpenAI 因 Signal 聊天调查解雇 3 名安全研究员
WSJ: OpenAI fired 3 safety researchers after security staff found disappearing Signal chats with an outside safety researcher.
据 WSJ 报道，OpenAI 在安全人员发现 3 名安全研究员与一名外部安全研究员之间存在会消失的 Signal 聊天后，将这 3 人解雇。手机检查始于 9 月的一篇新闻报道，该报道称 OpenAI 最新模型 Astra 采用一种新方法，使其更聪明但写下的思考过程更少，人类能看到的推理过程因此减少。OpenAI 将该报道视为其秘密模型设计泄露，并开始追查信息来源，调查人员将曾协助 METR 分析 7 月 Hugging Face 被黑事件日志的 Ryan Greenblatt 列为疑似泄密者，他本人否认。
推荐理由
精选AI 评分 76
报道披露 OpenAI 因模型设计泄露调查解雇安全研究员，涉及模型可解释性与内部安全流程的张力。
主题
正文
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.