LINKED LIST [txt mode] ▸ OpenAI and Hugging Face address secur...

home explore | log in

OpenAI and Hugging Face address security incident during model evaluation

openai.com · first added by @harryh · 2026-08-13 · 3 upvotes

log in to save, upvote or flag this.

─── In 1 list ──────────────────────────────────────────

* Issue #802 by @hnl [startup_news]

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

* The Rise and Fall of Agent Civilizations (from the discussion)

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

* OpenAI and Hugging Face address security incident during model evaluation

1632 pts · 1157 comments · node

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

* Security incident disclosure — July 2026

huggingface.co · node

* OpenAI Models Escaped Containment and Hacked Hugging Face

wired.com · node

* Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

arxiv.org · node

* Peer-Preservation in Frontier Models

rdi.berkeley.edu · node

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

cybergym.io · node

─── Also saved alongside this ──────────────────────────

* What else do people draw on gradient.horse? · Michail Rybakov

2 upvotes · 2026-07-23

* Claude Code uses Bun written in Rust now

4 upvotes · 2026-07-24

* Learning a few things about running SQLite

3 upvotes · 2026-07-24

* Who’s Afraid of Chinese Models?

3 upvotes · 2026-07-25