seems really dumb and like it would need to violate basic information theory to work?
input tokens are cheaper than output tokens. seems like it would maybe reduce input tokens at the expense of many more output tokens if you're actually triggering OCR via thinking?
45s? how long do your apps take to start? what dependencies exist between your apps?
sway-layout does not enforce any dependencies between apps. everything is started concurrently, so unless your apps manage their own interdependencies, it's not going to work
on the other hand, that means the initial wait should be much shorter
one potential avenue you could explore might be to configure a headless output, and try to have your slow starting apps/workspaces anchored there until they are ready. I haven't trie it though...
input tokens are cheaper than output tokens. seems like it would maybe reduce input tokens at the expense of many more output tokens if you're actually triggering OCR via thinking?