Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Microsoft releases Flint, a visualization language for AI agents

microsoft.github.io

Post reply on HN
Print view View original

91–100 of 149 posts

Re: Show HN: Microsoft releases Flint, a visualization language for AI agents

#91

Post by chenglong-hn »

shostack wrote: post #87
PunchyHamster wrote: post #76

Earlier quoted context omitted.

also worth noting that Vega-Lite is literally just fucking that and AI already does good job with producing JSONs for it

I work with someone who did a lot of work with this to improve our ability to generate awesome visualizations with little thinking. It's a very powerful language but needs guardrails and guidance, particularly if you want end users to be able to produce consistent and standardized visualizations without knowing anything about it.

Also guidelines sent to the agent may or may not get ignored if they are just part of the context :(

Re: Show HN: Microsoft releases Flint, a visualization language for AI agents

#92

Post by chenglong-hn »

drob518 wrote: post #75
fernie wrote: post #55

Earlier quoted context omitted.

But for that we already have mermaid.js (and its precursor Graphviz/dot). The only reason to use this instead of existing, mature ones designed for humans is if you are an AI agent.

Why can’t AIs generate for the “existing, mature ones?” Like the other commenter said, I’m not sure I get the “this is totally for AI” marketing. Why can’t AI use the existing ones and why can’t humans use this?

the design here has some constructs (i.e., semantic types) that AI can use better than human at generation time; and then the generated spec can be easy for user to edit since there is no need for hard-coded low-level parameters!

Re: Show HN: Microsoft releases Flint, a visualization language for AI agents

#93

Post by piterrro »

For a while now, everytime I see „for AI agents” Im looking for benchmarks with comparable solutions.

The only „for AI agent” solution that will gain adoption is/should be measured by two dimensions: token usage and correctness.

If the solution doesnt use less tokens than generating chart.js code for example - why should I use it?

Same for correctness, if the generated chart spec is correct only 90% of the time - why should I use it?

It’s still early but I think this is the direction we should be thinking about „for AI agents” libraries and projects.

Re: Show HN: Microsoft releases Flint, a visualization language for AI agents

#94

Post by chenglong-hn »

piterrro wrote: post #93

For a while now, everytime I see „for AI agents” Im looking for benchmarks with comparable solutions. The only „for AI agent” solution that will gain adoption is/should be measured by two dimensions: token usage and correctness. If the solution doesnt use less tokens than generating chart.js code for example - why should I use it? Same for correctness, if the generated chart spec is correct only 90% of the time - why…

Yes! correctness, expressiveness, reliability and cost (token + time)

Re: Show HN: Microsoft releases Flint, a visualization language for AI agents

#96

Post by chenglong-hn »

qiuwu wrote: post #95

Good points. Another step to be a middleware translator between LLM abilities to specific application area. It might lead to good or miss leading. While LLM ability boundry extends, it might invalid for next turn. Best Qiuwu

great point, I feel both the low-level foundation language and the high-level abstraction should evolve together, just like how human programming language evolves (e.g., frontend frameworks and libraries).

Re: Show HN: Microsoft releases Flint, a visualization language for AI agents

#97

Post by whattheheckheck »

pwarner wrote: post #28
cpard wrote: post #26

There’s an emerging pattern in agentic systems and this project is a great example. A deterministic layer like a compiler or generator of code with some kind of IR that the LLM generates and feeds it with. I feel we will be seeing this more and more in the near future.

When I first saw Claude generating PPT decks by writing Python code instead of making the XML directly, it was sort of an "aha moment" for me. This seems to be the path for many things. It also feels slightly limiting, and like a hack LONG term, but 100% correct approach for a while.

Have you seen marp? https://marp.app/

Re: Show HN: Microsoft releases Flint, a visualization language for AI agents

#98

Post by gofreddygo »

fernie wrote: post #55
bigfishrunning wrote: post #52

Earlier quoted context omitted.

But why be exclusive? Why not "Chart language for computer programs to generate"? I don't want to use an agent at all, but i wouldn't mind generating some charts with an easy-to-generate markup language...

But for that we already have mermaid.js (and its precursor Graphviz/dot). The only reason to use this instead of existing, mature ones designed for humans is if you are an AI agent.

Graphviz and mermaid are a shitshow.

anything more than their own handpicked examples and you're better off using d3 or yfiles. layering, clustering, boundaries, rearranging are all basic needs for text to diagrams. None support it.

Both suck at being any good for rendering diagrams from readable structured text. There is a gap to be addressed.

Re: Show HN: Microsoft releases Flint, a visualization language for AI agents

#99

Post by chenglong-hn »

gofreddygo wrote: post #98
fernie wrote: post #55

Earlier quoted context omitted.

But for that we already have mermaid.js (and its precursor Graphviz/dot). The only reason to use this instead of existing, mature ones designed for humans is if you are an AI agent.

Graphviz and mermaid are a shitshow. anything more than their own handpicked examples and you're better off using d3 or yfiles. layering, clustering, boundaries, rearranging are all basic needs for text to diagrams. None support it. Both suck at being any good for rendering diagrams from readable structured text. There is a gap to be addressed.

I find it lacks some easy way to do alignments or grouping, which makes editing frustrating. Could be a good language re-design opportunity.

Re: Show HN: Microsoft releases Flint, a visualization language for AI agents

#100

Post by ebeirne »

piterrro wrote: post #93

For a while now, everytime I see „for AI agents” Im looking for benchmarks with comparable solutions. The only „for AI agent” solution that will gain adoption is/should be measured by two dimensions: token usage and correctness. If the solution doesnt use less tokens than generating chart.js code for example - why should I use it? Same for correctness, if the generated chart spec is correct only 90% of the time - why…

I agree this is the right time to be exploring this more.
Post reply on HN