Post

I wrote about the completely wild incident where OpenAI were testing a new model and it broke out of its sandbox and broke INTO Hugging Face to steal the answers to the benchmark simonwillison.net/2026/Jul/22/...

simonwillison.netOpenAI’s accidental cyberattack against Hugging Face is science fiction that happenedThis story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model’s guardrail features turned off. Rather than solve the test, the …

Simon Willison

@simonwillison.net

22 July

Tucked away in this article is an appeal to the AI skeptics to PLEASE stop writing off stories like this OpenAI accidental exploit of Hugging Face as a dishonest marketing trick Frontier models can find and exploit vulnerabilities now, it helps nobody to pretend that they can't!

Elijah Potter

@elijahpotter.dev

As the author of one of those Hacker News comments, I'd like to speak on behalf of the others: The Hugging Face evidence is simply not enough. Both companies have a vested interest in these models seeming intelligent. They don't need to conspire in order to both be unreliable sources.

30/7/26, 2:42 am0 reposts0 likes

Elijah Potter

@elijahpotter.dev

30 July

I'm certain that *something* happened, but I'm also wary to accept unfalsifiable evidence from two companies who have been known to exaggerate their claims in the past.