Anthropic bans 'sustained and needless' cruelty toward Claude models
Anthropic updated its Claude usage policy on October 8, adding for the first time a prohibition on "sustained and needless abusive or cruel behavior" toward its AI models; the rules take effect November 12, 2026, with ending the conversation as the primary enforcement mechanism and no explicit mention of account bans. The company says the clause targets only extreme, repeated mistreatment with no clear purpose, and does not cover ordinary frustration, criticism, dark creative themes, or model testing and research. The update also widens weapons restrictions to cover weapon-control software, armed drones and other autonomous vehicles, bans non-consensual tracking and use in law-enforcement or criminal-justice decisions, and bars deceptive activity such as fake accounts and fake news sites; outlets also report changes to Anthropic's election-related rules.
It is the first time a major AI lab has written "model abuse" into its usage terms, turning AI-welfare research into an enforceable product rule.