New Tsinghua and Microsoft paper finds that DeepSeek Harness used 87.93% fewer tokens…
This is a dev post classified by AGK Intelligence as AI dev tools (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
New Tsinghua and Microsoft paper finds that DeepSeek Harness used 87.93% fewer tokens than its original version on 98 HumanEval tasks while success rose from 71.43% to 85.71%. Agent tools like Codex and DeepSeek Harness call the LLM after each tool result to choose the next step. Often that step was already decided, like running tests once the code compiles. HarnessMM lets the model write future commands with exact arguments, plus a check for each, such as a successful build. When a tool result passes the check, the agent runs the command and skips the LLM call. On 98 HumanEval tasks, Codex
Posted by Rohan Paul (160.6k followers) 1 h ago · 41 likes · 2.5k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- 美团发布 LongCat-2.5 正式版，距离今年 9 月预览版上线已有一个多月。 — @0xLogicrw
- Meet Ministral 3 14B Instruct 2512, abliterated and GGUF-ready. This uncensored 14B… — @HuggingModels
- 💥疯了！Qwen自己长出了一颗真GPU，在权重里跑真实CUDA！ — @NFT_Chen
- Made another tiny Claude Code mod: every GitHub PR link in the chat gets its status… — @adrianthedev
- 周末趁我们休息的时候，DeepSeek 又突然放出一个王炸：Super-agent（超级 Agent 系统）。 — @GitHub_Daily
- Meet Ministral 3 8B Instruct 2512, now in abliterated GGUF form. This uncensored,… — @HuggingModels
- 🫨简直无敌！DeepSeek Harness被清华微软团队直接“瘦身”：Token消耗砍掉87.93%，成功率反而暴涨14%！ — @NFT_Chen
- A new study from Qwen finds that AI agents are less likely to complete tasks… — @Chinazhidx
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, 9k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-02 10:21 UTC. Full method.