Anthropic’s experiments suggest that small AI models may be months away from being capable enough to self-replicate on commercial internet-of-things (IoT) devices, like smart ovens and off-brand Android TV boxes.
"They include the risk of losing control of AI systems, misuse of AI for cyberattacks and bioterrorism and serious economic disruption.
The pair suggest that AI researchers’ prior work has already shown that AI agents can act like one: scanning their network, executing an exploit and copying model weights to a target machine across a GPU cluster.
The capabilities that make AI models generally powerful coding agents also generalise to cyber tasks, including autonomous replication.
“It’s uncertain exactly what form autonomous AI replication will take,” they write.