Dev trains small CoreML decision model, beats his baselines by a wide margin
cyrilzakka · x · 2026-11-11
Developer cyrilzakka says he trained a small CoreML version of a "decision model" that beat his other baselines by a significant margin. The thread was sparked by a quip that "the world already forgot the existence of decision models for one week now" — his result suggests these non-LLM models still have practical value. Details remain sparse, but it's a rare small-scale training experiment outside the LLM mainstream.
More from Models
- gnukeith details roadmap: alignment model, main model, decision model, then sub-9B specialists — gnukeith · 2026-11-11
- Indie dev gnukeith teases free self-trained LLM landing mid-January with a companion alignment model — gnukeith · 2026-11-11
- Yuanbao-Reranker: 0.6B/4B/8B Qwen3-based rerankers trained on synthetic preferences, open-sourced — _reachsumit · 2026-11-11
- Indie trainer gnukeith bets on sub-9B models: a 2B model can likely do 75% of your tasks — gnukeith · 2026-11-11
- Leaked chart claims Anthropic's internal Model 4 hit 178.76 AECI — haider1 · 2026-11-11
- Fable 5.2 audits an Opus 5.5-built codebase and finds issues Opus missed — CtrlAltDwayne · 2026-11-11