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)→
More from coding & agent
- 6-minute Hubble documentary made with Claude and Jimeng CLI workflows — xiaohu · 2026-11-19
- Every on Claude Fable 5.2: Human Thinking at the Start Matters More as AI Builds More — every · 2026-11-19
- Semantic caching LLM answers by embedding similarity is unsafe — 138-pair test shows why — Narrow_Side_7778 · 2026-11-19
- Can ComfyUI refine existing mocap animations? A motion-to-motion workflow question — _Tito5_ · 2026-11-19
- Mycelium: an open-source framework that turns analytical project knowledge into a living dataset — arjunrajlab · 2026-11-19
- harness-hub open-sources RL-trained LoRA adapters tuned per agent harness, recipe coming Friday — yb2698 · 2026-11-19