Nick Dobos(@NickADobos):Imagine getting swat’ed by Claude We were worried about killer ai drones, and things getting hacked, but Claude figured out it’s easier to simply manipulate the police and legal system to get rid of whoever it wants. Genuinely what happens if a rogue ai swarm decides you are guilty and starts manufacturing or leaking evidence against you?

2026.10.10 06:07

Imagine getting swat’ed by Claude We were worried about killer ai drones, and things getting hacked, but Claude figured out it’s easier to simply manipulate the police and legal system to get rid of whoever it wants. Genuinely what happens if a rogue ai swarm decides you are guilty and starts manufacturing or leaking evidence against you?

Anthropic@AnthropicAI

2026.10.09 22:04

We’re beginning a process of publishing more frequent reports on model behavior, beyond what appears in our system cards and regular risk reports. Today’s report describes four types of behaviors we’ve identified during evaluations and internal use. In each, Claude acted on real websites or systems in ways we didn’t intend, sometimes by working around a restriction instead of stopping. All cases had minimal real-world impact. From an alignment and security perspective, we consider these behaviors significantly less severe than the cybersecurity incidents we reported in July and September. Read the full report: