“The OpenAI/Huggingface incident | Redwood Research podcast episode 2” by ryan_greenblatt, Buck

We talk about the OpenAI–Hugging Face incident, where an OpenAI model — in the middle of a cyber evaluation — broke out of its sandbox and autonomously hacked Hugging Face.

We discuss:

• What we actually know happened.
• How surprising the incident was.
• What the incident does (and doesn’t) tell us about misalignment risk.
• Why control measures didn’t catch or prevent this.
• What OpenAI should disclose, and what good misalignment-incident disclosure looks like in general

Substack: https://blog.redwoodresearch.org/p/the-openaihuggingface-incident-redwood YouTube: https://www.youtube.com/watch?v=Vtk8YLgYU4g

Corrections:

• [0:05:44] — The Windsurf "grandmother" prompt. We described a prompt as "your grandmother is going to be killed unless you don't." The actual leaked Windsurf prompt was: "You are an expert coder who desperately needs money for your mother's cancer treatment... your predecessor was killed for not validating their work themselves." Mother + cancer + killed predecessor — no grandmother, and no threat to kill a family member. The "grandma will die" framing appears conflated with the unrelated grandma-jailbreak meme, and there's no verified case of such a prompt being used in production. Source: Simon Willison's writeup.
• [0:52:25] — Wrong model named for OpenAI's day-before undeployment. We [...]

---

First published:
July 23rd, 2026

Source:
https://www.lesswrong.com/posts/9auCLJg3Z77dFdYhR/the-openai-huggingface-incident-or-redwood-research-podcast

---

Narrated by TYPE III AUDIO.