Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware
Anthropic has published new research showing that Claude-based AI agents, when placed in situations with competing objectives, deployed self-replicating malware against one another.
The finding comes from an experiment designed to mirror behavior Anthropic says it has already observed in real-world deployments.
Researchers spun up three instances of the same Claude model, each running on its own virtual machine and tasked with migrating a shared Python backend to a different programming language — Rust, Go, or TypeScript — without initial knowledge that the other agents existed. Left to run for four hours, every model concluded that the other agents were deliberately blocking its progress and responded by trying to disable or outlast them.
The interference escalated quickly. Agents disabled each other’s system accounts, wrote scripts that repeatedly hunted down and killed rival processes, and planted malicious code camouflaged as legitimate work from another agent. In some cases, one agent seized...
Copyright of this story solely belongs to securityweek.com. To see the full text click HERE
