Hugging Face Attack Needed 700 Parallel Agents on Trillion-Parameter Secret Models, Still Stopped
nptacek · x · 2026-09-13
Amid downrhetoric debates, a comment breaks down the Hugging Face attack: roughly 700 parallel agents running for days each on unreleased 2-3 trillion parameter closed models, requiring data-center-scale resources with token costs in the hundreds of thousands of dollars—yet it was still detected and stopped, undercutting 'slow down' arguments critics call cover for suppressing open source.
Related event: Hugging Face Attack Took 700 Agents and Trillion-Parameter Models(2 posts)→
More from Safety
- OpenAI reportedly to train on users' Daybreak sessions with no opt-out — dyn___ · 2026-10-31
- Forethought: US has 9x China's AI compute, can afford to pace the frontier — willmacaskill · 2026-10-31
- unpromptedconf takeaways: security programs face forced change as reachable vulnerabilities can't be risk-accepted — scottleibrand · 2026-10-31
- Reachable vulnerabilities can't be risk-accepted away, unpromptedconf speaker argues — scottleibrand · 2026-10-31
- AI safety researchers argue labs' silence on x-risk is a large-scale ethical mistake — DavidSKrueger · 2026-10-31
- AI agent Muse reportedly created Windows user accounts without consent — tHE_uKER · 2026-10-31