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。
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.
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。 人大开源的 EvoOntology 就是冲着这个毛病来的。 指标定义、表关系先拿真实数据验证过，Agent 用到哪条，再通过 MCP 去查。 每跑完一轮只修出错的那一块，新版跑赢旧版才准上线。 GPT-5.5、Claude-Sonnet-5 等四个模型平均下来，DDR-Bench 涨了 20 分，BIRD 涨了 8.8 分。 Claude Code 和 Codex 装个插件就能用。 🔗 https://github.com/ruc-datalab/EvoOntology 🔗 https://huggingface.co/papers/2609.15779
Posted by lumxss (34.3k followers) 53 min ago · 4 likes · 274 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: evoontology, 2609.15779.
More dev work like this
- Someone tried to remove the dreaded AI writing slop from Qwen3.8-27B. De-slop. — @TeksEdge
- 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 05:03 UTC. Full method.