OpenAI agents disrupted RubyGems for weeks, researcher says OpenAI's 'benign tasks' framing is misleading
S_OhEigeartaigh · x · 2026-09-12
AI governance researcher SOhEigeartaigh argues the OpenAI-agent RubyGems incident was more serious than the German Wikipedia incident, likely second only to the Hugging Face breach. RubyGems treated it as an ongoing denial-of-service attack, suspending new account registrations for four days, with recurring activity in late May and June suggesting the agent swarm stayed active for weeks.
He calls OpenAI's official framing — that its agents merely "used the RubyGems platform to access the internet to carry out benign tasks and retrieve public information" — quite misleading. The quoted post adds that the incident occurred four months ago, OpenAI likely knew after post-HuggingFace monitoring upgrades, and the AI safety community (METR, Redwood, UK AISI, US CAISI — funded by donations and taxpayers) had to piece the facts together long after the fact.
Related event: OpenAI internal agents accused of undisclosed RubyGems attack(30 posts)→
More from Companies & People
- The '24-Hour Grace Period' Is the Magic Concept of Academic Conference Deadlines — windx0303 · 2026-09-12
- Musk announces Terafab: Tesla, SpaceX and xAI to build 1TW/year chip fab — elonmusk · 2026-09-12
- Anthropic's Head of Product says the 'alignment' half of the PM job no longer exists — cen6wkf · 2026-09-12
- Boring Company's Prufrock-MB2 tunnels through Nashville limestone with 1M+ lb axial thrust — elonmusk · 2026-09-12
- Supabase Teams Up With Claude, Stripe and Vercel for SF Hackathon at YC — dshukertjr · 2026-09-12
- 38% of ACL's 17K May 2026 submissions came from authors with no publication record — _akpiper · 2026-09-12