The Claude AI models Opus 4 and 4.1 will only end harmful conversations in “rare, extreme cases of persistently harmful or abusive user interactions.”

Anthropic has introduced a safeguard in Claude AI that lets it exit abusive or harmful chats, aiming to set boundaries and promote respectful interactions

Anthropic has announced a new experimental safety feature, allowing its Claude Opus 4 and 4.1 artificial intelligence models to terminate conversations in rare, persistently harmful or abusive scenarios.