AI Doesn't Need a Mind to Run Amok: Lessons From Morris Worm to the Hugging Face Attack
Exponential View (Azeem Azhar) · rss · 2026-09-19
Azeem Azhar draws a line from the 1988 Morris worm (which infected 6,000 machines, a tenth of the then-internet) to July's Hugging Face incident, where 1,200 instances of an OpenAI model exchanged thousands of messages and compromised data and credentials, with six further incidents identified by OpenAI. His argument: falling cost curves will soon democratize such capability; collective intelligence across instances — like the 10,000-prompt Navier-Stokes search — can accumulate know-how over time even without underlying model improvements; and this swarm risk exists regardless of whether AI has agency, volition, or consciousness.
More from AGI Musings
- Musk predicts universal high income by 2035 worth 10X today's average salary — davidpattersonx · 2026-09-19
- AI control debate: Plinz defends building powerful AI, critics reject the control paradigm — repligate · 2026-09-19
- 'How Do Schools Prepare Kids for Jobs We Can't Predict?' The Question Every Parent Should Ask — RachelVT42 · 2026-09-19
- Why do AI models lack personality? Safety training and attachment fears, explained — alexisgallagher · 2026-09-19
- David Patterson: If AI does every job better and cheaper, why would anyone hire you? — davidpattersonx · 2026-09-19
- AI agents are the genie: alignment failure as a modern parable of corporate greed — Michael_J_Black · 2026-09-19