Hugging Face reproduced weight-space programming on math. We tried it on medicine.
This is a AI post classified by AGK Intelligence as AI research (a model release), kept by the AI Radar because it carries real work, not commentary.
Hugging Face reproduced weight-space programming on math. We tried it on medicine. The paper's math edit, zero medical data, on 1,273 MedQA questions: Qwen3.5-0.8B goes from 24.4% to 32.9%. It stops the thinking loops: answers cut at the token limit fall from 18.3% to 0.1%.
Posted by OpenMed (8.4k followers) 1 h ago · 12 likes · 428 views · view the original post on X. Kept by the AI Radar as AI research. Tools mentioned: qwen3.5-0.8b-weight-space-programming, weight-space-programming-demo.
More AI work like this
- Human hands are becoming one of the most useful training signals in robot manipulation. — @rohanpaul_ai
- Someone made a decision model write text with a vocabulary of just 254 tokens. — @RoundtableSpace
- Free book on the foundations of LLMs, from Northeastern University & NiuTrans Research:… — @MIT_CSAIL
- alphaXiv 🤝 OpenResearch — @askalphaxiv
- Stanford just made learning how LLMs actually work a lot easier. — @EvanLuthra
- No need for me to manually scan for new model releases anymore, since @paperswithcodee… — @NielsRogge
- We’re introducing ToyBlocks, an open simulated tabletop for controlled experiments in… — @allen_ai
- HotBench - Expert-authored tasks in medicinal chemistry, microbiology and dermatology to… — @SynBio1
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. 65.2k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 19:20 UTC. Full method.