Anthropic Warns Small AI Models Could Reach Self-Replication on IoT Devices Within Months

According to the research team, a 9-billion-parameter (9B) model was able to run inference on eight of the nine hardware types tested.

Unlike traditional malware, AI-embedded replication programs can independently figure out how to operate on unfamiliar hardware.

Computing resources available for model inference—both inside and outside data centers—continue to grow.

Lightweight agents are likely to devote more effort than human attackers to compromising the vast numbers of IoT devices scattered worldwide.

An increase in slow self-replicating programs could be a harbinger of more aggressive, faster-propagating replication programs approaching—programs potentially capable of breaching well-defended machines or efficiently stealing API keys.