Sacks shares point-by-point debunk of the "self-replicating AI worm" claim
DavidSacks · x · 2026-10-13
David Sacks amplified gmkurtzer's point-by-point rebuttal of the claim that AI models can self-replicate and spread like worms without datacenter infrastructure:
- No self-replication: a controlled test harness spawned the agents
- No hacking: access was deliberately left unauthenticated
- No agency: agents were explicitly instructed to propagate
- No autonomous survival or defensive behavior; tiny models lacked capability while capable models ran elsewhere
- 15 devices managed only 0.39 tokens/sec
- No demonstrated real-world infection or propagation
Conclusion: the experiment was engineered to succeed and still failed to support the headline — "orchestrated automation dressed up as a rogue AI threat. Fear isn't evidence."
More from Safety
- DOE puts $159M into Genesis projects, expanding OSPREY agent that runs particle accelerators — omnivaughn · 2026-10-14
- OpenAI Studies Internal Signals Behind AI 'Metagaming' During Training — WormLivesMatter · 2026-10-13
- AI Safety Incident: Command Injection Via a Reference Tool Copies a Source File — WormLivesMatter · 2026-10-13
- AI self-replication across 2M smart TVs would need just 40 H100s, researcher calculates — peterwildeford · 2026-10-13
- XBOW Details Chrome Full-Chain Exploit: 3 Bugs, 6 Days, $250K Google Bounty — moyix · 2026-10-13
- Giving LLMs tools makes them worse at refusing harmful requests, up to 68.7% — lateinteraction · 2026-10-13