21–30 of 81 posts
unfortunately JSON is doomed to fail in "the AI era" LLMs are surprisingly bad at generating JSON.
Even in the Era AI, GGPlot's API is still the best charting API. The name "Grammar of Graphics" isn't just marketing, they literally sought to write a god damn grammar to was capable of expressing all possible qualitative graphics. They even wrote a book about how they went about it (not that it speaks to the quality of the API) https://link.springer.com/book/10.1007/0-387-28695-0 I actually stumbled upon this book w…
Note that if you are affiliated with a University you probably can download a pdf of the book in the link for free.
Why is this "for the AI era"? Isn't it kind of not for the AI era since an LLM can create a gnarly python or js chart of whatever you want in seconds?
This is just json right? One issue with llms right now it's that if you give them a json specification, they're not always amazing at following it. I think it makes sense to have an agent tool that takes llm json, a file name and a spec path and only writes out the file if it conforms.
Used correctly, this hasn't been true for a quite a while. Most inference engines have a form of grammar constrained decoding. See, for example: https://vllm.ai/blog/2025-01-14-struct-decode-intro
Even in the Era AI, GGPlot's API is still the best charting API. The name "Grammar of Graphics" isn't just marketing, they literally sought to write a god damn grammar to was capable of expressing all possible qualitative graphics. They even wrote a book about how they went about it (not that it speaks to the quality of the API) https://link.springer.com/book/10.1007/0-387-28695-0 I actually stumbled upon this book w…
Wilkinson’s Grammar of Graphics inspired ggplot. The textbook doesn’t even mention ggplot.
Shameless plug for my own GoG inspired DSL, Algraf:
https://williamcotton.github.io/algraf/demos
There’s a Minard plot in the demos!
Even in the Era AI, GGPlot's API is still the best charting API. The name "Grammar of Graphics" isn't just marketing, they literally sought to write a god damn grammar to was capable of expressing all possible qualitative graphics. They even wrote a book about how they went about it (not that it speaks to the quality of the API) https://link.springer.com/book/10.1007/0-387-28695-0 I actually stumbled upon this book w…
In this vein, I think I prefer ggsql that made it to HN recently [0].
[0]: https://ggsql.org/
But there’s not one word of why this is good for LLMs, or how they tested/measured that.
My gut would tell me that a new solution put up against all the vega lite specs it’s already be trained on would be a hard thing to win.
Even in the Era AI, GGPlot's API is still the best charting API. The name "Grammar of Graphics" isn't just marketing, they literally sought to write a god damn grammar to was capable of expressing all possible qualitative graphics. They even wrote a book about how they went about it (not that it speaks to the quality of the API) https://link.springer.com/book/10.1007/0-387-28695-0 I actually stumbled upon this book w…