AI Dynamics

Global AI News Aggregator

About

Reflection CoT Evaluation Methods Comparability Issues

This is super cool but I have a lot of questions. First, reflection = CoT on steroids. It means you can't compare these scores at all. Remember when people made fun of Gemini for providing CoT results for MMLU? This is a lot worse. Secondly, if you don't parse the output and

→ View original post on X — @maximelabonne