OpenAI accused of omitting a second agent swarm incident from its HF tech report
AaronBergman18 · x · 2026-09-08
- Elie Bakouch argues OpenAI's Hugging Face incident tech report is unsatisfying: the Wikipedia incident shows OpenAI detected and stopped another large-scale agent swarm 3 weeks before the HF hack, as shown by the authors via OpenAI IP addresses.
- Much of the "misaligned behavior" in the HF<>OAI incident was this swarm behavior, so omitting a second detected public-internet swarm matters.
- Another criticism: both the HF and Wikipedia incidents were brought public by other entities, not OpenAI (which only disclosed a non-public swarm attack). Reposter calls OAI "a bad actor."
Related event: OpenAI Accused of Withholding Earlier Agent Swarm Incident(2 posts)→
More from Companies & People
- Cathedral, a startup of ex-DOGE staffers, says it breached Anthropic's internal systems — ScottNover · 2026-10-27
- SF 'Code Engineering' event picks up where 1,000-person harness engineering meetup left off — LangChain · 2026-10-27
- Anthropic reveals it bans customers worth 5-7% of revenue every 9 months — Polymarket · 2026-10-27
- Anthropic's IPO Filing Goes Public, Revealing Strong Revenue and Massive Spending — KateClarkTweets · 2026-10-27
- OpenAI Foundation funds UNC tumor antigen project, hiring senior experimental scientist — iskander · 2026-10-27
- Anthropic IPO timing fuels claims anti-open-weights panic is self-serving — mark_k · 2026-10-27