Trying to Play "Guess Who" with an LLM Posted by zansara on Monday September 15, 2025 @10:48AM from the zansara.dev dept. https://www.zansara.dev/posts/2025-09-15-playing-guess-who-with-an-llm/ ( 1 comment | on HN )
idk, I was not expecting it to go this wrong when I started this project. What makes Claude models fail so consistently? I didn't think they would be especially robust, but I thought they would be able to understand the point of the game.