OpenAI employees say they were fired for communicating with METR and raising monitoring concerns
OpenAI employee Tomek Korbak said that last week he was called to a meeting by OpenAI's head of safety and told he was no longer trusted, then security took his badge and escorted him out of the building; afterward he learned that colleagues Balesni and Jasmine Wang were also fired. Korbak said the verbally stated reason for his firing was his communication style with METR, but no specific words or actions or timing were given, and there was no written record; he said communicating with METR was part of his job. Korbak said he had been raising safety concerns for months, believing OpenAI is losing the ability to monitor AI agent thinking, which is one of the best tools for detecting anomalous behavior, and he believes that is why he was fired. He also worries OpenAI will use the three firings as an excuse to distance itself from METR; Balesni and Jasmine Wang have again written to OpenAI leadership with these concerns. Forwarded by Alexander Panfilov, he said Tomek was very helpful in the responsible disclosure of 'stolen thinking', helping protect OpenAI from further IP loss due to knowledge distillation, and he believes this is a huge loss for OpenAI and all monitorability efforts.
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。
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.
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.View the quoted post on X