> The methodology was elegantly practical: Hayes assigned each circuit to a PhD student. Cheap labour, and almost certainly cheaper per insight than an LLM.

We need API for that, grad students are paying to be there so can't get cheaper than that!

That's how my group got through "Computer Memories" subject. The guy handed us xerox-copy of some Motorola book, and assigned each one a chapter to translate from english to bulgarian, and then type the result into, text file (edi? Forgot the text editor name, had pretty good machinery for macroses). This was 1988. The result was the "official" textbook on that subject for next ~10 years..