Zach Daniel on Mythryl: “We need a way to validate approaches to how we work with LLMs to…”

We need a way to validate approaches to how we work with LLMs to write code, and we need to start developing the dataset. I've laid some groundwork here, but I need help. Tear it up, critique it, but most of all, PR some evals y'all. #ElixirLang github.com/ash-project/...

github.comGitHub - ash-project/evals: Tools for evaluating models against Elixir code, helping us find what works and what doesn'tTools for evaluating models against Elixir code, helping us find what works and what doesn't - ash-project/evals

24/6/25, 12:17 am7 reposts10 likes

Post