Small artificial intelligence models may be months away from being able to copy themselves onto everyday internet-connected devices, such as smart ovens and off-brand Android TV boxes, Anthropic said on Monday.
In its experiments, the AI company tested whether models could find vulnerable devices, copy themselves onto them and keep spreading without human help. It found that small models, with fewer than 30 billion parameters, could complete many of the individual steps needed to replicate, but struggled to carry out the whole sequence from start to finish.
In simplified tests, with some security steps removed, GLM-5.2 and stronger models were able to replicate from start to finish, Anthropic said.
If small models keep improving at their historical rate, they will be able to replicate autonomously by the end of this year, with small weight-based replicators following soon after, the company warned.
Replicating models would be hard to shut down because there is no central off switch, Anthropic said. Unlike conventional malware, they could also work out unfamiliar devices on their own, including data centre processors.
The research focused on internet-of-things (IoT) devices, including Android TVs, smart appliances and other connected gadgets, because they are typically poorly secured.
Anthropic said such autonomous AI systems were likely to replicate slowly and to rely on widely available, relatively insecure computing resources. It said systems should be strengthened to make it harder for such AI agents to spread.
(Information from Reuters)
