Someone made a decision model write text with a vocabulary of just 254 tokens.
This is a AI post classified by AGK Intelligence as AI research (a tool drop), kept by the AI Radar because it carries real work, not commentary.
Someone made a decision model write text with a vocabulary of just 254 tokens. >A trimmed GPT-2 token set, with fragments like "ing" removed so Jev stops looping >It picks one token at a time and feeds each choice back in
Posted by 0xMarioNawfal (271.1k followers) 1 h ago · 12 likes · 26.1k views · view the original post on X. Kept by the AI Radar as AI research.
More AI work like this
- Hugging Face reproduced weight-space programming on math. We tried it on medicine. — @OpenMed_AI
- 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
- I wonder if you realize how interesting this is. — @SciTechera
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 18:21 UTC. Full method.