AI Dynamics

Global AI News Aggregator

Claude Model Evaluation Bias in Character Assessment

By

@steipete

–

I'm working on character evals and noticed that Claude would constantly pick itself as #1, so I removed the model names from the judge and changed things.

→ View original post on X — @steipete,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *

MORE ARTICLES