我拿 JEV 全自动挑战了一个复杂的任务：帮我考Claude官方的课程认证
This is a AI post classified by Jev as AI agents (a tool drop), kept by the AI Radar because it carries real work, not commentary.
我拿 JEV 全自动挑战了一个复杂的任务：帮我考Claude官方的课程认证 这次难度非常大：整整 67 个章节，里面夹了 8 套测试题，要求 AI 必须自己不停地滑动翻页，同时还要把各章节最后动态弹出的测验全答完，这次我仍然只丢了个网址，大概4 分钟它自己刷完了整个Anthropic课程，做完 90 道题，全程零人工干预 不过实话说，这次 JEV 并没有做到一次性全通：8 套测验虽然高分拿下了 7套 Passed（连最变态的 28 题终极大考都一把过了），但最终还是有一套测验没到 80 分，而且分数非常低，只有14分...导致官方结业徽章卡在临门一脚，差点就直接拿到了哈哈🤡 不过这次测试完全能看出 JEV 的真实能力，在面复杂场景下，它的自主识别和复杂判断能力基本干到了 85% 左右，继续优化，争取下次直接一把！ 视频为我剪辑过的答题精华部分，其他的翻页识别的就不放出来了
Posted by 梭哈.AI (33.5k followers) 1 h ago · 4 likes · 1.5k views · view the original post on X. Kept by the AI Radar as AI agents.
More AI work like this
- I HAVEN'T OPENED CLAUDE AT MIDNIGHT SINCE I BUILT THIS FOLDER — @polydao
- Tencent ARC Lab just released GameHorizon Suite — @HuggingPapers
- launch update 🎉 — @alexwestco
- Introducing a new way to EDIT with @typesafeai Jev and gemini flash lite. — @Saboo_Shubham_
- some executor v2 stuff i'm excited about — @RhysSullivan
- adorable stories with muse y'all — @olegakbarov
- AI is changing the landscape of the working world at rapid pace. But what does this mean… — @PwC
- 说下我成功的几点经验： — @viprhz
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. 41.2k 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 09:46 UTC. Full method.