Someone just made ordinary Qwen behave a LOT more like Jev without training a new model.
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.
Someone just made ordinary Qwen behave a LOT more like Jev without training a new model. 🏆 TOP Jev Clone (according to HF leaderboard) 🎯JEVfire takes an existing open LLM and changes how it makes decisions. Instead of prompt → generate { → key → : → value → comma → … It gives Qwen a fixed menu of legal answers, reads the model’s scores, picks the winners, and builds the JSON in code. No retraining. No second model. No autoregressive JSON serialization. On Qwen3.8-27B-FP8 + vLLM ... 4 decisions 🐌 JSON generation: 878 ms ⚡ JEVfire: 110 ms 🚀 8× faster 28 decisions: 🐌 JSON: 5.11 sec ⚡ JEVf
Posted by David Hendrickson (11.3k followers) 1 h ago · 0 likes · 82 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- OMG Opus 5.5 just made this — @notjazii
- InclusionAI just open sourced a design model that can create a finished graphic, and a… — @aijoey
- Have you ever had a local coding agent flying at the start of a session and crawling an… — @jvr0x
- ☄️GPT-6 from @OpenAI is now available on AIsa — @AIsaOneHQ
- ☄️GPT-6 from @OpenAI is now available on AIsa — @AIsaOneHQ
- Meet Victoria: a text generation model that's lean and mean. It uses MoE pruning, REAP,… — @HuggingModels
- inline editing in neovim using opencode — @maddestfhd
- Stop re-explaining your codebase before every planning chat. — @DanKornas
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. 22.4k posts from 5k X accounts over the last 21 days, 2.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 12:49 UTC. Full method.