jawnston · HN

made a fun little website with AI to explain how the Oceans in FFIX are authored after days of slamming my head against the keyboard trying to deconstruct it

heliostatic · HN

A couple weeks ago we were on vacation with friends, and after the kids were asleep we played games -- mostly Qwirkle, which I had never played and am terrible at. I don't care about being terrible at games, so I made a web version to keep playing after vacation: build lines of tiles that share a color or a shape, 2-4 players (or add bots). I wanted it to be low friction, so there are no accounts. Your identity is an anonymous id in localStorage, and you can move it to another device by scanning a QR code or hitting a unique url. Start a game and text someone the link (game slugs are semi-memorable three word phrases), or "Play the computer" and you can play immediately against bots. Games are async-friendly with web push for turn notifications. The stack is one Node process on a small VM, Next.js + Socket.IO, no database. The server and the client use the same engine so moves validate optimistically, and the bots go through the same functions, so bot moves are always legal. State is

@LinguExcel · X

Become fluent in any language faster than ever by reviewing thousands of real life sentences. Treat language learning like a HIIT workout.

@polycontext · X

Context-aware localization for apps, games, and software.

@Ghofrane7a2l · X

Check out what I just built with Lovable!

@DevSanghav15604 · X

The Duolingo for everything. Type in a prompt and get a full, personalized course built for you.

lecsium · Product Hunt

Lecsium Learn languages by reading AI-generated interactive novels

@hkbonur · X

that digitalise paper forms and make everything multi language, so businesses can get better conversion. One form any language.

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

@Caleb_L509 · X

ai voice translation for calls

@JRABARA1 · X

Mid-Century Teak Scramble download freighter app, dm your wallet serves as feedback :)

Seamless Canvas — AI 无缝纹理生成器，通过文字描述或上传图像生成可平铺纹理 - [更多介绍](https://seamlesscanvas.com)