Get the Brief
AnthropicResearchMateriality 2

Anthropic study warns small AI models could self-replicate across devices

Anthropic published a study finding small AI models may soon spread on their own across poorly secured consumer devices such as smart TVs and robot vacuums. In tests, one model completed the full infection chain, and CEO Dario Amodei warned a swarm could form a persistent botnet within 6 to 12 months.

First seen 13 Oct, 10:33 UTC on The Decoder2 sourcesLast update 2h ago

What the sources say

Linked, never rewritten. Official means the lab itself.

Official0

No word from Anthropic yet.

Press2

The Decoder· 13 Oct, 10:33Anthropic study warns that small AI models could soon replicate across everyday devicesArs Technica· 14 Oct, 12:55Anthropic warns small AI models could self-replicate through IoT devices

How it unfolded

Every source in the order it appeared. Times in UTC.

13 Oct 10:33The Decoder Anthropic study warns that small AI models could soon replicate across everyday devices14 Oct 12:55Ars Technica Anthropic warns small AI models could self-replicate through IoT devices

Keep up with Anthropic