零人工答题！Claude 官方结业徽章正式到手🫡 全程 100% 靠 JEV + 小模型自主完成
This is a AI post classified by Jev as AI agents (a tutorial), kept by the AI Radar because it carries real work, not commentary.
零人工答题！Claude 官方结业徽章正式到手🫡 全程 100% 靠 JEV + 小模型自主完成 我听说有人拿这个免费证书在简历上写“Claude 认证 AI 工程师”？😂 好了不开玩笑，这次用 JEV 跑复杂任务踩坑的坑，绝对能帮你省下大量排错时间： 第一次跑极其顺利，一口气自动跑完了 85% 的内容。但剩下那 15% 却遭遇严重卡壳，连续排查修改了四五次才彻底搞定（仅限此场景）👇 1. 决策太快把白屏当作完成了 JEV 的离散决策只需几十毫秒，但现代前端组件异步挂载往往需要几百毫秒。网页还没完全渲染出新元素，JEV 就已经做完决策并判定“无内容”直接跳步了。实际的情况就是 JEV 的速度实在太快了，题目还没弹到下一题他就判断结束了.... 2.零视觉感知，缺乏自我纠错机制 JEV 完全不看屏幕画面，也没有大模型的反思推理链（No CoT），它完全盲信外部脚本喂给它的 DOM 列表。一旦发生过度滑动导致目标元素滚出可视区域，或者页面布局发生偏移，传统视觉 Agent 能“看一眼”自我修正，而 JEV 没有任何画面感知，只会在残缺的候选池里机械打转 3.System 1 直觉模型缺乏长程规划 JEV 的定位是极速的“条件反射”，本身没有多步状态机的规划能力。如果在动作候选池里同时暴露了局部操作与全局终态按钮（比如 Save / Submit / 确认），模型在遇到中
Posted by 梭哈.AI (33.6k followers) 1 h ago · 1 likes · 1.3k views · view the original post on X. Kept by the AI Radar as AI agents.
More AI work like this
- Enterprises are rapidly adding AI agents across platforms 💻 — @Gartner_inc
- @demian_ai — @demian_ai
- I Gave an AI Agent 6 Hours to Build Two Vision Models — @LearnOpenCV
- Browserbase (@browserbase) is now available in Merge Agent Handler. — @merge_api
- Xiaomi has officially open-sourced the new MiMo-V2.6 family, featuring two native… — @itsvishaltwt
- NVIDIA Isaac ROS 5.0 brings AI agents to robotics development. 🤖 — @NVIDIARobotics
- How RL training can generalize to any harness and any task? — @bookwormengr
- META 🔥: Muse agent is being prepared to get integrations with Telegram, Messenger, and… — @testingcatalog
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 41.7k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 14:48 UTC. Full method.