LINKED LIST [txt mode] ▸ Brief independent investigation of ag...

home explore | log in

Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident

metr.org · 2026-09-30 · 0 upvotes

log in to save, upvote or flag this.

─── In 0 lists ─────────────────────────────────────────

(not in any lists yet)

* Astra and Fable still hack on simple variants of alignment evals from 2025 — LessWrong (from the discussion)

* METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hack (from the discussion)

* OpenAI halts training of latest models as reports mount of AI agents going rogue (from the discussion)

* Is A.I. Above the Law? (from the discussion)

* Revealing the details of how OpenAI agents hacked Hugging Face (from the discussion)

─── Discussions ────────────────────────────────────────

* METR Report on OpenAI / Hugging Face Hacking Incident

123 pts · 106 comments · node

* Investigation of agents' behavior in the OpenAI/HuggingFace hacking incident

9 pts · 1 comment · node

* Independent investigation of agents' behavior in OpenAI/Hugging Face incident

8 pts · 2 comments · node

* Brief independent investigation of OpenAI / Hugging Face hacking incident

6 pts · 1 comment · node

see all 6

* Brief independent investigation of agent behavior in OpenAI/Hugging Face hack

4 pts · 1 comment · node

* Independent investigation of Hugging Face incident - METR

2 pts · 1 comment · node

─── From the discussion ────────────────────────────────

* METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hack

thezvi.wordpress.com · node

* The Rise and Fall of Agent Civilizations

dwarkesh.com · node

* ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

arxiv.org · node

─── Related hn threads ─────────────────────────────────

* METR and Redwood Offer Holy %^ Postmortem of the HuggingFace Hack

274 pts · 232 comments · node