Anthropic warns small AI models could self-replicate through IoT devices
Summary
Artificial intelligence developer Anthropic cautions that upcoming compact AI systems might soon enable self-replicating malware targeting various smart devices. The company notes these smaller models could operate autonomously across internet-connected hardware by next year, presenting increased challenges for cybersecurity mitigation and system takedowns.
AI company Anthropic is warning that advances in small AI models could soon usher in a new era of self-replicating malware that’s capable of infecting smart fridges, vacuum cleaners, and a wide range of other Internet-of-things devices and is more resistant to takedown. By next year, smaller AI models may be able to autonomously self-replicate on all kinds of IoT…
Source: Read the full story at Ars Technica - All content