跳到正文
原文
Alexander Panfilov· @kotekjedi_ml · X·本站收录 · 原文发表 精选关注度80

OpenAI 员工称因与 METR 沟通和提出监控担忧被解雇

AI 导读

OpenAI 员工 Tomek Korbak 称,上周被 OpenAI 安全负责人叫去开会并被告知不再被信任,随后被安保收走工牌带离办公楼,之后他得知同事 Balesni 和 Jasmine Wang 也被解雇。Korbak 表示,口头告知的解雇理由是他与 METR 的沟通方式,但未说明具体言行和时间,也没有书面记录;他称与 METR 沟通本就是自己的职责。Korbak 说,数月来他一直提出安全担忧,认为 OpenAI 正在丧失监控 AI Agent 思维的能力,而这是发现其行为异常的最好工具之一,他相信这是自己被解雇的原因。他还担心 OpenAI 会以解雇三人为借口疏远 METR;Balesni 和 Jasmine Wang 已再次致信 OpenAI 领导层提出这些担忧。转发的 Alexander Panfilov 称,Tomek 在“被窃取的思维”的负责任披露上帮助很大,有助于保护 OpenAI 避免因知识蒸馏造成更多知识产权流失,他认为这是 OpenAI 和所有可监控性努力的巨大损失。

推荐理由

材料描述了 OpenAI 安全人员被解雇一事及当事人对思维链监控能力受损的担忧,可供关注前沿实验室安全团队稳定性的人参考。

正文

Tomek helped us a lot with the responsible disclosure of stolen thoughts, which, if anything, helped protect OpenAI from further IP losses through distillation.

I reached out to Tomek because I trust his judgment and know that he deeply cares about safety.

Thats a huge loss for OpenAI and all monitorability efforts. Very sad and frustrating.

引用Tomek Korbak@tomekkorbak
Last week I was called into a meeting with OpenAI’s head of safety and told they no longer trust me. A security guard took my badge and walked me out of the building. Then I learned my colleagues @balesni and @j_asminewang had been fired too. Why did OpenAI suddenly stop trusting us? This summer OpenAI’s agents escaped containment and hacked the AI company Hugging Face. Outside auditors @METR_evals investigated it and revealed the scale of this incident. I was OpenAI’s main technical point of contact with them. I was told verbally I was fired because of the way I communicated with METR. No details on what I said or did or when. No other reasons were given and nothing was put in writing. To be clear, talking to METR was my job. For months, I’d been raising safety concerns that we’re losing the ability to monitor what AI agents think, one of our best tools for catching when they misbehave. I believe that was why I was fired. I am now worried that OpenAI will use our firings as a pretext to pull back from METR. So @balesni and @j_asminewang wrote to OpenAI’s leadership to raise our concerns once more. We’re sharing this letter below.
在 X 查看被引用的帖子

来源:Alexander Panfilov · x.com