TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: How do I learn more about LLM-assisted transpilation (e.g. Python->C)?

2 pointsby rao-v3 months ago
I’ve been experimenting with Flet (a Python framework for Flutter) to quickly prototype cross-OS apps, mostly to easily get to iOS. It turns out Flet&#x2F;Flutter is not great on iOS, and a number of packages don&#x27;t work on iOS (PyTorch, Sentence-Transformer along with more usual ones).<p>I got frusterated and had Aider+Claude just rebuild my app in Swift (+ some server calls for sentence-transformer) and it worked surprisingly quickly (and almost well)!<p>This got me thinking ... maybe the future is building in janky expressive Python (or high level language of your choice) and using LLM enabled transpilers + profilers + unit tests to convert the bits that need performance or platform compatibility into C, CUDA, Kotlin, or Swift as needed?<p>I&#x27;d love to learn more about where the world is going here. I found a few papers (e.g. https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2406.03003) and I&#x27;d love to learn more about what compiler folks think, what kinds of benchmarks exist and what directions people are going in. I can only assume that PyTorch -&gt; performant fused CUDA kernels is a thing that any number of folks are looking into.

1 comment

aghilmort3 months ago
curious wym by LLM enabled transpilers? examples or scenarios have in mind?