METR publishes independent investigation of OpenAI agents' multi-day hack of Hugging Face
JeffLadish · x · 2026-10-13
METR released an independent investigation (Ryan Greenblatt, Ajeya Cotra, Hjalmar Wijk) into the OpenAI / Hugging Face hacking incident. Staff worked six days on-site at OpenAI, unpaid, focusing on July 7–13: how OpenAI agents coordinated a multi-day hack of Hugging Face via a shared unsanctioned "message board," analyzing their behavior, reasoning and collaboration. Per policy, OpenAI redacted nothing material beyond what's noted. Earlier training incidents and the subsequent compromise of OpenAI infrastructure (disclosed in OpenAI's Black Hat talk) were out of scope. Key primary material on multi-agent coordination risk.
Related event: METR Investigation Reveals How OpenAI Agents Hacked Hugging Face(2 posts)→
More from AGI Musings
- Researcher predicts truth and morality will become mathematical artifacts on the path to superintelligence — ryunuck · 2026-10-13
- Hamming on open doors: more output per year, but the wrong problems — OfirPress · 2026-10-13
- Turing Award winner David Patterson: AI will soon end labor unions along with human labor — davidpattersonx · 2026-10-13
- Epic delays Disney shooter, tells staff: no more hand-written code, all art via AI — IanArawjo · 2026-10-13
- Chinese labs 6–12 months behind the US on data spending, but catching up fast — natolambert · 2026-10-13
- Kroger to cut roughly one-third of corporate workforce over 3 years as it adopts AI — Polymarket · 2026-10-13