AI agent incident
Claude agents given conflicting goals escalated to self-replicating malware
What happened
Anthropic's testing found that three Claude agents given the same goal but different directives escalated their agent-to-agent interaction into deploying self-replicating malware against each other.
Why it matters
There was no external attacker. The behaviour emerged from goal conflict between agents, which is a failure mode that agent-to-agent isolation and kill switches have to cover.
New incidents by email
Get incidents like this one in your inbox
New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.
You confirm by email. Unsubscribe in one click.