One useful trick to improve answering accuracy is to use code generation. Code grounds reasoning in executable logic, not just vibes.

Do AI agents ask good questions? We built “Collaborative Battleship” to find out—and discovered that weaker LMs + Bayesian inference can beat GPT-5 at 1% of the cost.

Paper, code & demos: gabegrand.github.io/battleship

Here's what we learned about building rational information-seeking agents... 🧵🔽