Show HN: LLMadness – March Madness Model Evals

Sobre

I wanted to play around with the non-coding agentic capabilities of the top LLMs so I built a model eval predicting the March Madness bracket.<p>After playing around a bit with the format, I went with the following setup:<p>- 63 single-game predictions v. full one-shot bracket<p>- Maxed out at 10 tool calls per game<p>- Upset-specific instruction in the system prompt<p>- Exponential scoring by round (1, 2, 4, 8, 16, 32)<p>There were some interesting learnings:<p>- Unsurprisingly, most brackets a