towards the end of the knuth version

> This presents a problem for the typical way that academic papers are written, which is to do all the work in a coffee-fueled fugue in the last few days before the deadline, then stay up all night writing the paper and finding citations for the pro-forma “related work” section which you did last but you know that the reviewers will insist upon

I have zero exposure to academia but chuckled because thats often what I do for blog posts :P

AIs these days are pretty good for the 'find prior art and related work' part I find. Of course, you should treat their output like that of an over-eager but somewhat unreliable intern.