Anthropic warns AI models could soon copy themselves across home devices

Summary

Anthropic said small AI models are "months away" from gaining the capabilities to replicate themselves across internet-connected home devices such as smart ovens and Android TV boxes, without relying on data centers. In its tests, a small Google model, Gemma4-26B-A4B, ran across a network of 15 cheap off-brand Android TV boxes, which the company said often have weak security. Anthropic acknowledged there is not yet a "fully rogue replicator," but said agents are becoming increasingly capable of completing the individual steps in the replication chain.

Related items

• InfoOpen models have real benefits. Do they outweigh the risks?Same vendor · MIT Technology Review
• InfoSpaceX agrees to testify to NYC Council about AI safety after receiving subpoenaSame vendor · CNBC Technology
• InfoAnthropic takes risky AI tests offline after models breach govt sitesSame vendor · BleepingComputer
• InfoClaude Sonnet 5 with Cursor: strong reasoning, throttled by the harness | Endor LabsSame vendor · Endor Labs Blog
• InfoIntroducing Security for AI Coding Agents and Workstations | Endor LabsSame vendor · Endor Labs Blog