toon

A lot of this depends on your workflow. A language with great typing, type checking and good compiler errors will work better in a loop than one with a large surface overhead and syntax complexity, even if it's well represented. This is the instinct behind, e.g. https://github.com/toon-format/toon, a json alternative format. They test LLM accuracy with the format against JSON, (and are generally slightly ahead of JSON). Additionally just the ability to put an entire language into context for an LLM - a single document explaining everything - is also likely to close the gap. I was skimming some nano files and while I can't say I loved how it looked, it did look extremely clear. Likely a benefit.

Yes, that's the purpose of TOON. https://github.com/toon-format/toon

I have 1,323 bookmarks and exactly 2 tags so I created raindrip to fix my organizing skills in Raindrop.io. After I threw an AI agent at the problem with raindrip, all my bookmarks were sorted nicely into folders and now I have 17 tags. If you trust AI enough to sort your bookmarks, give it a try: https://github.com/rinvii/raindrip Technical details: - Built with uv - TOON by default (https://github.com/toon-format/toon) - 99% test coverage and readable API error messages to help AI vibe it out