Get the latest tech news

Claude's Character

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

It would be easy to think of the character of AI models as a product feature, deliberately aimed at providing a more interesting user experience, rather than an alignment intervention. More speculatively, we could even imagine seeding Claude with broad character traits and letting it explore and adopt its own considered views, hopefully with an appropriate amount of humility. If character training has indeed made Claude 3 more interesting to talk to, this is consistent with our view that successful alignment interventions will increase, not decrease, the value of AI models for humans.

Get the Android app