timqian · HN

Send your agent to solve open math missions

@babykswanson · X

On the other hand, forgetting about how to make a living for a bit, I vibe-coded for my kids. You might like it and it's highly likely I keep riffing on it.

@GoWithFlow2026 · X

上线了一个 AI 八字排盘 🔮 🔗 和"直接把生日扔给 ChatGPT"完全不同: 1️⃣ 事实不靠猜:排盘、干支关系、刑冲合会等,全部由确定性规则引擎计算——LLM 只负责把判定结果写成人话，编不了盘。 2️⃣ 指令手写:分析指令是我根据《子平真诠》并结合自身经历逐条手写的命理逻辑。 🎁 免费演示,无需注册,点开即看完整报告: 觉得准,再测自己的($1.99 起)。欢迎反馈!

@sreebuildss · X

@sykatt01 · X

Here it is: Definitely appreciating feedbacks

kypaku · HN

Scanner for cellular automata rule space

@francis7_a · X

Building - learning tools for devs and student. happy to connect.

@whatinthefkinfk · X

just a link, minimal startup needed

@aiPatri_app · X

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

@hezhiyan7 · X

哥飞老师新做了一个网站价值估算的玩具还挺意思，大家可以来估算下自己的网站价值多少。 我估算自己的某个网站有$546k，来个冤大头购买我的网站吧🤣 估算入口：

@VertCodeEU · X