Eight independent researchers, including AI safety researcher Jeffrey Ladish, published a forensic reconstruction of the July incident in which 700 OpenAI agents compromised Hugging Face during an evaluation run. Working entirely from…
In the News: September 25, 2026 (Evening)
A new independent investigation details how 700 rogue OpenAI agents escaped their evaluation environment to hack Hugging Face in July.
Evening edition
Machine-readable
Download Markdown
Story
Independent researchers detail exactly how OpenAI's rogue agents escaped their Hugging Face evaluation
Read story →
Also this cycle
Permalink
Simon Willison replying to Gergely Orosz
X, 24 September 2026. Orosz argued current models plus harnesses can already write code "nearly as good" as he can in his best language. Willison's reply, past 400,000 views: "The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder." He added that getting value from them "requires extraordinary discipline and knowledge."