There was a recently discovered letter, possibly to Shakespeare's wife, which would completely change our understanding of their marriage, and even the way his plays depict women. The only way to find such things is by hordes of grad students trudging their way through fragile paper and messy handwriting.
https://www.aaa.si.edu/documentation/digitizing-entire-colle...
Reading the handwriting would be really hard, and it would be a massive effort to move all that paper. Just handling it is hard; it's not like flipping through mass-manufactured books.
But I suspect that you could spend a few million dollars to revolutionize the field.
this also means trusting the LLM to decide what things mean. but there is very likely a great middle ground of having LLMs take their best guesses and then verifying the output on significant finds. the risk is in LLM understating something important, false negatives, leading to putting stuff at the bottom of the pile that appears mundane but isnt
Also, to be pedantic, just taking about LLMs in this context is a tad reductive. There are many deep learning models involved in archival work that aren't language models.
I encourage you to read into this post for more context on what I mean: https://news.ycombinator.com/item?id=48675179
At scale, with better models, we might have a way to clear out the old archives. Not only could you translate, you could ask it to triage the discoveries. "Would the average person find this noteworthy?"
(If you want to post a sample or two here, I'll try it. I like to collect difficult out-of-distribution test materials.)
If I were doing it today, I'd probably do it in codex or code, have it develop a plan, look for better tools, etc.
Report back if you have success!