Hacker News Reader

> We wanted to find a way to deterministically group elements that should be translated together, so, for example, a phrase wrapped in the `<a>` link tag wouldn't get mistranslated because it was processed in isolation. We also wanted to detect inline function calls and handle them gracefully during compile-time code generation.

Very cool

View on HN

Thanks! To make it work predictably, we actually tested quite a few different algorithms before landing on one that produces outputs LLMs can reliably understand.

Conceptually, we're relying on common sense assumptions about how developers structure JSX. We assume you write reasonably semantic markup where the visual hierarchy matches the code structure - no CSS tricks that make the UI render completely different from what the JSX suggests.

This let us create translation boundaries that make intuitive sense to both developers and AI models.

Reply on news.ycombinator.com