After training it's iteration: cleaning data usually beats tweaking hyperparameters

ziv_ravid · x · 2026-11-19

A Hebrew X thread fragment on the post-training loop: it's mostly iterations — train, look at where the model fails in eval, figure out what kind of traces are missing or noisy, fix, and repeat. In general, cleaning the data helps more than playing with hyperparameters or model type, though it depends on the problem.

Related event: Before and After Training: Skill Distillation and Data Iteration(2 posts)→

Original post →

More from coding & agent

coding & agent channel →