codeinabox@programming.dev to Programmer Humor@programming.devEnglish · 2 months agoYou can save at least 40% by externalizing the CSSprogramming.devimagemessage-square57linkfedilinkarrow-up1385arrow-down12
arrow-up1383arrow-down1imageYou can save at least 40% by externalizing the CSSprogramming.devcodeinabox@programming.dev to Programmer Humor@programming.devEnglish · 2 months agomessage-square57linkfedilink
minus-squareMonkderVierte@lemmy.ziplinkfedilinkarrow-up55arrow-down1·2 months agoThey didn’t think of just letting it generate the text (usually Markdown) and then processing it to HTML? Wait, the LLM does the “thinking” there.
minus-squarechicken@lemmy.dbzer0.comlinkfedilinkarrow-up5·2 months agoI assume there’s some context for why there is an argument to begin with between whether to prompt for markdown vs html, and what this is actually for
minus-squareMonkderVierte@lemmy.ziplinkfedilinkarrow-up2·2 months agoWell, i’ve got polls via excel via email at work, so…
minus-squarenickiwest@lemmy.worldlinkfedilinkarrow-up3·1 month agoI assume that if it isn’t already happening, future models will have instructions to maximize token usage.
They didn’t think of just letting it generate the text (usually Markdown) and then processing it to HTML?
Wait, the LLM does the “thinking” there.
I assume there’s some context for why there is an argument to begin with between whether to prompt for markdown vs html, and what this is actually for
Well, i’ve got polls via excel via email at work, so…
I assume that if it isn’t already happening, future models will have instructions to maximize token usage.