[–] nsonha 2y ago ↗ Why not generate something less opinionated like plain css instead of tailwind. [–] jsyang00 2y ago ↗ too verbose probably, factoring in tokens cost [–] vanpelt 2y ago ↗ Tailwind is especially well suited for LLM generation because all of the styles come inline with the HTML. Could definitely just ask it to write styles but this approach also improves token efficiency.
[–] vanpelt 2y ago ↗ Tailwind is especially well suited for LLM generation because all of the styles come inline with the HTML. Could definitely just ask it to write styles but this approach also improves token efficiency.
4 comments
[ 4.6 ms ] story [ 20.8 ms ] thread