devwithjev
— reading now— views
Submit a build

Jev Maze-Solving Prompt Tests

ShikangS tested Jev in a maze-solving setup, comparing a baseline approach with variants that added exploration history, maze-algorithm guidance, and revised prompting.

View on X
ShikangS@SShikang𝕏
看了@karminski3这个测试觉得很有趣 但是总觉得Jev能力不至于此，于是在这套框架基础上补充测试了多组结果，详见视频。 首先是对照组： C0 —— 这个就是牙医的整活随机算法，随机游走。 C1 —— 这个是专业的迷宫算法，类似机器人走迷宫比赛会用到的。 C2 —— 这个是让gpt-5.6-luna模仿类似方法，在同一个Session里一步步探索迷宫。 然后是实验组，全部都是基于Jev的方案： E0 —— 这个就是牙医的Jev, 的确卡死在一个局部���优里 E1 —— 这个是在牙医Jev的基础上，扩充了上下文，包括全部历史操作以及已观察到的地图 E2 —— 这个是把专业迷宫算法的思路，用自然语言告知了Jev，并提供了全部通道经过次数的统计 E3 —— 这个是在E1的基础上，优化了prompt，删除多处对剩余距离的强提示，转而让Jev自己思考最佳策略 简单总结一下结论： 1. 站在成功率和性能视角： 专业算法 > Jev+专业Knowhow > Jev + 通用思路 > LLM 2. Jev的主要价值： - Jev自带智能，如果你不具备解题最佳实践，Jev可以替代一部分专业算法； 如果你具备最佳实践, 不必再用代码实现它，直接告诉Jev就行； - Jev比LLM快且省 3. Jev需要更好的prompt engineering以及harness： - 对比E0 和 E1, 增
Sep 23, 2026X postsView on X
The tests also included random-walk and professional maze-algorithm controls, plus a GPT-5.6-Luna control. The author reports that specialized algorithms performed best and that Jev benefited from added context and domain know-how.

Also filed under Tools & apps

  • Jev: a "System One" model that only makes decisions, $0.042 per million tokens with output free. 40-second explainer of why it matters for automation

    Jev: a "System One" model that only makes decisions, $0.042 per million tokens with output free. 40-second explainer of why it matters for automation Jev launched on Sep 15 from TypeSafe AI (founder Diogo Almeida, ex-OpenAI, credited on ChatGPT/InstructGPT). It does not generate text; it returns typed decisions (Choice / Score / true-false) with confidence. Price is $0.042 per million input tokens, output free. In its first week it became the fastest-adopted model on Vercel's AI Gateway, TypeSafe paused signups on Sep 22, Browser Use released jev-ultrafast (a web agent where Jev picks each action; Google Flights search in 7.1 s), and jaredpalmer/kev is an Apache-2.0 clone built on Qwen3.5 you can run yourself. My take in the video: the expensive part of automation was never the writing, i

  • Untitled

    There's a new AI model that refuses to talk. While everyone debates what a "decision model" is even for, builders already shipped the answer. 7 things people built with Jev in 9 days. Number 5 broke my brain 👇

  • Untitled

    I loved this idea so much that it deserves a share ❤️ I recently asked people to share what they’ve built with JEV, and then this guy 👤 shows up with an entire website dedicated to different JEV use cases! That’s honestly pretty cool. If you’re curious about JEV and want to see how it can actually be applied, definitely check this out. Huge shoutout to Animesh Mishra (@thatcasualvc) for the wonderful share 🙌 This is exactly the kind of stuff I love seeing from builders. 🚀

  • I built a Jev-based model router for Pi for automatic model selection

    I built a Jev-based model router for Pi for automatic model selection When Jev came out, one of my first thoughts was: could something this fast and cheap pick which model should handle an agent’s next turn? So I built plugin for Pi that uses Jev to choose the model and thinking effort. The idea is to send routine work to cheaper models and reserve the expensive ones for harder tasks. In Pi, the model mappings are configurable, and you can pin a model when you disagree with the router. I’ve been using them for a few days, and so far they’ve been working well for me. In my own evaluation, routed usage came to $141 at list prices versus an estimated $166 for Opus 5.5 on every request - about 15% less. That’s one developer’s data, though. The baseline is a pricing comparison, not a separate