I wonder how this does compare with D2 ( https://d2lang.com/ ) which also produces svgs
My first feeling is I find the syntax too verbose compared to D2. Plus I wonder if it solves the main problem of D2, which is the orientation of diagrams.
I don't get what is the risk here of "taking control" (cf. Dupe) of an AI here. For what I understand, it's that the API token are exposed. What are the capabilities of LLMs that are "dangerous" ? Or maybe I misunderstood/missed something.
Yes I tried it, thanks !
I like it and it's nicely thought, unfortunately I ran into a few weird issues when pasting code or editing code. I need to see if there is one already opened on this. Or open a new one with steps to reproduce the issues. Will do.
Wow, you did a lot of releases since then !
I was running the 0.1.15, so it can explain some discrepancies.
No problem on linux with the last release, will try the "freshly" released 0.1.97 on windows also (I think the issue was on this OS).
And I promise I'll create an issue if I encounter some difficulty.
For those who're interested, feel free to check out the develop branch and compile it for the latest build. I’d love to hear your feedback and suggestions for PNANA.
reply