Someone tried to remove the dreaded AI writing slop from Qwen3.8-27B. De-slop.
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Someone tried to remove the dreaded AI writing slop from Qwen3.8-27B. De-slop. It worked, but then the coding agents started looping. So they went back and fixed that too. Here it is, Qwen3.8-27B NoSlop V2. 👀 Using Heretic's training-free weight modification, RefinedNeuro changed the model's behavior without conventional fine-tuning. Writing test responses containing selected AI clichés Original Qwen → 86/100 NoSlop V2 → 65/100 👈 Desloped! But here's why V2 exists. Coding-agent runs stopped for looping or no progress Original Qwen → 2/120 NoSlop V1 → 20/120 😬 NoSlop V2 → 6/120 Coding-
Posted by David Hendrickson (12.7k followers) 1 h ago · 6 likes · 448 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- AI 查公司数据最坑的地方，是它会把 uid 和 user_id 混为一谈，最后算出一个看着挺像样的错数。 — @bkdgiffug
- Gemini now has a dedicated developer console for testing custom apps. — @mrfanduu
- Another stealth model 👀 — @ItsmeAjayKV
- i did not know these were real — @theaaron
- Just tried this. I connected the Excalidraw+ MCP to T3 Code through http://Toolport.app… — @btsouth
- Anthropic 把自家做 Claude 应用的示范代码整套放了出来，GitHub 上已经 1.8 万 star。 — @bkdgiffug
- vLLM gave Local AI AMD users something more interesting than another decode speedup. — @TeksEdge
- 28 paid model calls a week just to say "no change." 𝗛𝗲𝗿𝗺𝗲𝘀 Agent skips them. 💸 — @BkashJosi
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 04:58 UTC. Full method.