完整作品展
技术栈
60 projects
扫描购物小票发现省钱机会，如价格差异和折扣。
@Qintarisapp · X
订单管理应用，帮助销售代表追踪利润和配送
@JwjwF67346 · X
Check out what I just built with Lovable!
用 Chrome 扩展和网页编辑器将屏幕截图转化为精美设计。
@buildwithshyam · X
在 Free Market 上浏览、购买和出售农产品及手工商品。
@JoshuaHenr3593 · X
Just launched: Free Market (FMK) 🛒 A free marketplace for sellers, artisans & delivery riders — inventory tools, sales tracking, and profiles, no fees. Check it out 👉 RTs appreciated 🙏 #FreeMarket #FMK #buildinpublic
在Kalshi天气预测市场中发现数据驱动的交易机会。
@WingGirlTrader · X
Because the edge is in trading weather markets. And the is a free tool that provides real edge almost daily in temperature bets. And it's FREE
用 AI 驱动的模拟考试和闪卡学习 NEET 生物学。
@devjedi404 · X
I'm currently working on PrepPilot an AI-powered platform for NEET preparation. Added around 8k questions in total. The entire process was tiring but learnt a lot. For now you can access PrepPilot here :
让AI模型通过3D动画展现香蕉植物的完整生命周期来比较性能。
fran-mora · HN
I gave 5 AI coding agents one prompt: grow a banana plant through its whole life in three.js: sprout, leaves, flower, fruit, rot, then pups that restart the loop. It's deceptively simple and yet very hard to get right from procedural code: you have to write working three.js and understand how the plant is actually built; how it hangs, ages and decays. Get the biology wrong and the code renders something weird. These are agents, not bare models (Claude Code and Codex for now). They can use tools, including playwright to check their work and improve it.
AI蘑菇识别工具，快速准确，包含毒性检查和危险相似种警告。
Mushroom Identification — 蘑菇 AI 识别工具（快速、准确)，结果包含毒性、高危相似种警告
粘贴广告获得 AI 点评和 Butter Score，然后重写以优化转化。
@HowardYHuang · X
Flint是为AI代理设计的可视化语言,用于创建交互式数据可视化。
chenglong-hn · HN
Data visualizations are the bridge between user and data. But building AI agents that can generate visualizations reliably can be very tricky: - simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make visual decisions that are supposed to be handled by a good compiler. Flint is a visualization intermediate language to address this issue, allow AI agents to solve this last-mile human-agent interaction problem. It provides a simple semantic-type based specification, and contains a layout optimization engine that can produce good-looking charts (filled with derived low-level details) from simple
Wetter 支持本地计算和自定义聚合模式的天气预报和可视化应用。
__mp · HN
I built my own weather prediction / visualization app: https://wx.rsp.li (on-device temperature lapsing, on device interpolation modes, user-selectable aggregations, etc…). One of these days I should do a writeup. I also asked Claude to build a photo gallery for me https://places.pascalspoerri.ch (HDR, map support, similar images)
