A model that spends tokens reasoning can help train another model to make decisions…
This is a dev post classified by AGK Intelligence as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
A model that spends tokens reasoning can help train another model to make decisions without generating answer tokens. This is one of the most interesting ideas in a new paper on Foundation Decision Models. Researchers at Nace AI describe a training method called Reinforcement Learning from Adjusted Feedback (RLAF). Instead of training only against a single correct label, they use two sources of feedback: → A verified outcome, when one is available. → A generative reasoning model that assigns probabilities to the available options. For Drex Max, the judge is the generative Qwen3.8-27B base m
Posted by Tech with Mak (48.6k followers) 1 h ago · 10 likes · 905 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: Console by Nace.AI.
More dev work like this
- An American AI 🇺🇸startup released a top decision 27B model. 👀 — @TeksEdge
- I'm going to be in San Francisco next week speaking at @aiDotEngineer about the three… — @kentcdodds
- 推荐个挺有意思的开源项目 Moyu，专治 AI 写代码时爱自作主张的毛病。 — @bkdgiffug
- This Echo Dot sat in a closet for at least 4 years. — @markfenner
- Soniox STT v6 delivers our most accurate and fastest voice typing yet across 60+… — @soniox_ai
- NXP i.MX95 export for Ultralytics YOLO has shipped! 🚀 — @ultralytics
- Your agent wrote the report. Now give it a layout. — @DanKornas
- Introducing our next generation of model routers: — @OpenRouter
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. 31.8k posts from 5k X accounts over the last 21 days, 9.5k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 17:41 UTC. Full method.