Comment by neom
1 day ago
I've been complaining on hn for some time now that my only real test of an LLM is that it can help my poor wife with her research, she spends all day every day in small town archives pouring over 18th century American historical documents. I thought maybe that day had come, I showed her the article and she said "good for him I'm still not transcribing important historical documents with a chat bot and nor should he" - ha. If you wanna play around with some difficult stuff here are some images from her work I've posted before: https://s.h4x.club/bLuNed45
People have had spotty access to this model for brief periods (gemini 3 pro) for a few weeks now, but its strongly expected to be released next week, and definitely by year end.
Oh I didn't realize this wasn't 2.5 pro (I skimmed, sorry) - i also haven't had time to run some of her docs on 5.1 yet, I should.
While it's of course a good thing to be critical the author did provide some more context on the why and how of doing it with LLM's on the hard fork podcast today [0]: mostly as a way to see how these models _can_ help them with these tasks.
I would recommend listening to their explanation, maybe it'll give more insight.
Disclosure: After listening the podcast and looking up and reading the article I emailed @dang to suggest it goes into the HN second chance pool. I'm glad more people enjoyed it.
[0]: https://www.nytimes.com/2025/11/14/podcasts/hardfork-data-ce...
> ...of an LLM is that it can help my poor wife with her research, she spends all day every day in small town archives pouring over 18th century American historical documents.
> I'm still not transcribing important historical documents with a chat bot and nor should he
Doesn't sound like she's interested in technology, or wants help.
It doesnt have to be perfect to be useful. If it does a decent job then your wife reviews and edits, that will be much faster than doing the whole thing by hand. The only question is if she can stay committed to perfection. I dont see the downside of trying it unless she's worried about getting lazy.
I raised this point with her, she said there are times it would be ambiguous for both her and the model, and she thinks it would be dangerous for her to be influenced by it. I'm not a professional historical researcher so I'm not sure if her concern is valid or not.
As a scientist, I don't think this is valid or useful. It's very much a first year PhD line of thought that academia stamps out of you.
This is the 'RE' in research, you specifically want to know and understand what others think of something by reading others' papers. The scientific training slowly, laboriously prepares you to reason about something without being too influenced by it.
1 reply →
I think there's a lot of meta thought that deserves to be done about where these new tools fit. It is easy to off handedly reject change, especially as a subject matter expert who can feel they worked so hard to do this and now theyre being replaced so the work was for nothing. I really dont want to say your wife is wrong, she almost assuredly is not. But it is important to have a curious mindset when confronted with ideas you may be biased against. Then she can rest easy knowing she is doing her best to perfect her craft, right? Otherwise she might wake up one day feeling like symbolic NLP researchers trying LLMs for the first time. Certainly a lot to consider.
1 reply →