Okay, so specialized decision models are becoming the rage.
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Okay, so specialized decision models are becoming the rage. Bespoke Labs just released Nimble, an open 9B decision model built from Qwen3.5-9B. And apparently they built it in ONE DAY. The recipe: 🧠 Qwen3.5-9B 🎯 LoRA fine-tune 📚 only 2,676 training examples ❌ no Jev distillation ❌ no RL ✅ open model ✅ open data ✅ open training recipe Instead of generating explanations or JSON, Nimble scores the allowed answers: YES / NO → A / B / C → route 1 / 2 / 3 → severity 1–5 Then returns the choice + probabilities. Example of Bespoke's 324-example held-out test: Qwen3.5-9B → 66.36% Qwen3.8-27B
Posted by David Hendrickson (11.1k followers) 2 h ago · 31 likes · 1.5k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Did you already know, that you can interact via CLI with the apple foundation models? — @haukejung
- A new benchmark called JevBench just dropped. — @rohanpaul_ai
- Stop burning turns rewriting vague AI prompts — @DanKornas
- I WOKE UP TO MONEY — @michael_chomsky
- we launched the most comprehensive ai performance engineering repo in the world — @wafer_ai
- Structures a Claude Code session into a game studio with 49 specialized AI agents and 73… — @tom_doerr
- Jev is cool. So is it's OSS companion, Laya. — @BenjDicken
- I think we’re looking for this — @vaibcode
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 15.1k posts from 4.7k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 22:52 UTC. Full method.