this post was submitted on 28 Mar 2025
28 points (93.8% liked)

BestOfLemmy

8572 readers
1 users here now

Manual curation of great Lemmy discussions and threads

founded 2 years ago
MODERATORS
top 3 comments
sorted by: hot top controversial new old
[–] [email protected] 3 points 6 days ago
[–] [email protected] 3 points 6 days ago (1 children)

It's like a story told or written is based on some thing or some event. If humanity can develop a proper AI to collate and corroborate from all sides and views, we might be able to calculate the correlational probability of an historical event.

[–] [email protected] 2 points 6 days ago

Oh, that’s a very good point. I’ve already seen one LLM service that aims to summarize selected scientific sources and write articles based on them. You could feed it a bunch of historical texts and ask it to write an article based on them.

I’ve seen it sort of work with scientific articles, but those tend to be really short compared to historical records. AFAIK, even the normal GPT has some token limit, which you’ll run into during longer conversations. If you want to dump a bunch of diaries and logbooks on an LLM to answer a specific question about the motivations behind the development of flintlock rifles, you’re definitely going to run into some limitations.