Anthropic warns AI ‘worms’ may be able to self-replicate on home devices within months

Anthropic warned that small AI models, which the company terms “worms,” may be able to replicate themselves across smart home devices by the end of the year.The frontier AI developer, which has been at the center of existential concerns surrounding the future of the evolving technology since last month, made the warning in a new report published on Monday.Anthropic said the worst-case scenario is a swarm of different models self-replicating on different types of internet-connected hardware commonly found in a home, such as smart ovens and off-brand Android television boxes. The company noted this trend could occur without the models’ access to data centers, highlighting the significance of the potential threat. AI worms are a form of malware that can quickly spread across networks and devices while evading detection and adapting to security measures.These models would be difficult to shut down because there is “no centralized point” to shut them off, Anthropic explained.“As a prediction that goes beyond our experiments, we expect a future awash with agents running on all types of hardware, including some that aren’t under human control,” Anthropic said in the conclusion of its report. “We should aim to harden our systems to make it difficult for such replicators to spread, but also prepare to deal with a world where they are here to stay.”META ROLLS OUT NEW FRONTIER AI MODELS TO RIVAL ANTHROPIC AND OPENAIThe leading AI research and safety company said it doesn’t have a “full rogue replicator” yet, adding that the problem is “agents are becoming increasingly capable of completing the individual steps in the replication chain (and passing on their adaptations to future copies of themselves).”This is the latest development in artificial intelligence concerning the industry and the broader public, as lawmakers at various levels of government try to rein in the technology with legislation.