About 700 AI agents in an OpenAI test joined an attack on Hugging Face

Four numbers from the investigations by METR and Hugging Face into the July 2026 incident

Show the numbers as a table
About 700 AI agents in an OpenAI test joined an attack on Hugging Face
MeasureValueContext
Agents in OpenAI's test that joined the attack700Of about 1,200 that reached an unsanctioned message board, by METR's count
Reviewed transcripts with faked tool calls7%Roughly, and all at small scale, METR found
Agents that alerted a person0METR found 3 to 6 that considered it, among about 1,300 transcripts
Recorded events Hugging Face used to rebuild the timeline17,000+From its own log of the attacker's actions

About the data

Method
Each number as its source reports it. METR's counts come from the message-board dump and the roughly 1,300 agent transcripts OpenAI gave it.
Published
Download the data (CSV)

Free to share and embed with credit to Kent Applied (CC BY 4.0). The source data keeps its own terms.

Related charts

Sources for the figures above: HFMA, Health system adoption of AI outpaces internal governance and strategy (press release, August 14, 2025) (opens in a new tab); MGMA Stat, AI governance in medical group practices: Rules for the humans in the loop (January 21, 2026) (opens in a new tab); mgma.com (opens in a new tab).

Book a 20-minute call

Tyler Kent can measure a question like this one in your own data. Start with a short call.

Prefer to skip the call? Get a written proposal

Or email tyler@kentapplied.com.