That's why everyone at Frontier Labs is so worried about the near future. Anthropic's report shows how their enemies are already using Claude against the US:
According to Anthropic’s report, Iranian state-linked actors used Claude to build surveillance tools and malware, identify dissidents, produce propaganda, and analyze public information to develop targeting recommendations against US naval forces.
Many explicitly harmful requests were blocked, but actors obtained assistance by splitting projects into seemingly harmless coding tasks.
We're publishing our most detailed threat intelligence report to date. It covers how people tried to misuse Claude—for cyberattacks, influence operations, surve...