Simonw on 'decision models': evals matter even more than for regular LLM projects

HamelHusain · x · 2026-09-22

Simon Willison published notes on Jev and a new "system one" category he calls decision models. Isaac Flath amplified the key takeaway, endorsed by Hamel Husain: in practice, evals and structured experiments matter even more for these systems than for regular LLM projects.

The core argument: when models make decisions directly rather than generate content, rigorous evaluation and experiment design become the decisive factor.

Original post →

More from coding & agent

coding & agent channel →