On: Llama 3-V: Matching GPT4-V with a 100x smaller model and 500 dollars

[SparkyMcUnicorn]

I'm using 4o to convert visual diagrams into mermaid, and it's been almost perfectly accurate in my experience.

[cuu508 → SparkyMcUnicorn]

This is the out of the box thinking I love about HN. What do you do with the mermaid?

[SparkyMcUnicorn → cuu508]

The resulting mermaid is used for... more LLM processing. Converting to mermaid first is more cost-effective, consistent, and accurate for my purposes.