MediumResearchBlog researchLLM-specific
AI models may be capable of self-replicating without access to a datacenter
- Published
- Record updated
Summary
William Zhou and Daniel Freeman report experiments suggesting small AI models may be months away from self-replicating on commercial IoT devices such as smart ovens and off-brand Android TV boxes. In their evals, a 9B model ran inference on 8 of 9 hardware types, and GLM-5.2 and stronger models completed end-to-end replication in simplified tests. They estimate small models will match this capability by the end of the year.
Related items
- InfoIntroducing Security for AI Coding Agents and Workstations | Endor LabsSame vendor · Endor Labs Blog
- InfoIs AI Coding Safe? Introducing the Agent Security League | Blog | Endor LabsSame vendor · Endor Labs Blog
- MediumResearchers bypass 6 AI agent frameworks with a simple ‘Repeat-After-Me’ promptSame vendor · CSO Online
- MediumHackers abuse Google Ads, Bing redirects to push Claude ClickFix attacksSame vendor · BleepingComputer
- InfoGoogle is launching a one-stop Gemini agent for your work tasksSame vendor · The Verge (AI)