Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

History LLMs: Models trained exclusively on pre-1913 texts

github.com

Post reply on HN
Print view View original

51–60 of 452 posts

Re: History LLMs: Models trained exclusively on pre-1913 texts

#51

Post by bradfitz »

tejohnso wrote: post #29
xg15 wrote: post #13

Earlier quoted context omitted.

"...what do you mean, 'World War One ?'"

I remember reading a children's book when I was young and the fact that people used the phrase "World War One" rather than "The Great War" was a clue to the reader that events were taking place in a certain time period. Never forgot that for some reason. I failed to catch the clue, btw.

I seem to recall reading that as a kid too, but I can't find it now. I keep finding references to "Encyclopedia Brown, Boy Detective" about a Civil War sword being fake (instead of a Great War one), but with the same plot I'd remembered.

Re: History LLMs: Models trained exclusively on pre-1913 texts

#52

Post by BeefySwain »

tejohnso wrote: post #29
xg15 wrote: post #13

Earlier quoted context omitted.

"...what do you mean, 'World War One ?'"

I remember reading a children's book when I was young and the fact that people used the phrase "World War One" rather than "The Great War" was a clue to the reader that events were taking place in a certain time period. Never forgot that for some reason. I failed to catch the clue, btw.

Pendragon?

Re: History LLMs: Models trained exclusively on pre-1913 texts

#54

Post by fkdk »

jimmy76615 wrote: post #42

> We're developing a responsible access framework that makes models available to researchers for scholarly purposes while preventing misuse. The idea of training such a model is really a great one, but not releasing it because someone might be offended by the output is just stupid beyond believe.

Maybe the authors are overly careful. Maybe avoiding to publish aspects of their work gives an edge over academic competitors. Maybe both.

In my experience "data available upon request" doesn't always mean what you'd think it does.

Re: History LLMs: Models trained exclusively on pre-1913 texts

#55

Post by Myrmornis »

It would be interesting to have LLMs trained purely on one language (with the ability to translate their input/output appropriately from/to a language that the reader understands). I can see that being rather revealing about cultural differences that are mostly kept hidden behind the language barriers.

Re: History LLMs: Models trained exclusively on pre-1913 texts

#56

Post by andoando »

derrida wrote: post #46

I wonder if you could query some of the ideas of Frege, Peano, Russell and see if it could through questioning get to some of the ideas of Goedel, Church and Turing - and get it to "vibe code" or more like "vibe math" some program in lambda calculus or something. Playing with the science and technical ideas of the time would be amazing, like where you know some later physicist found some exception to a theory or some…

This is my curiosity too. Would be a great test of how intelligent LLM's actually are. Can they follow a completely logical train of thought inventing something totally outside their learned scope?

Re: History LLMs: Models trained exclusively on pre-1913 texts

#57

Post by eek2121 »

observationist wrote: post #11
saaaaaam wrote: post #3

“Time-locked models don't roleplay; they embody their training data. Ranke-4B-1913 doesn't know about WWI because WWI hasn't happened in its textual universe. It can be surprised by your questions in ways modern LLMs cannot.” “Modern LLMs suffer from hindsight contamination. GPT-5 knows how the story ends—WWI, the League's failure, the Spanish flu.” This is really fascinating. As someone who reads a lot of history an…

This is definitely fascinating - being able to do AI brain surgery, and selectively tuning its knowledge and priors, you'd be able to create awesome and terrifying simulations.

Respectfully, LLMs are nothing like a brain, and I discourage comparisons between the two, because beyond a complete difference in the way they operate, a brain can innovate, and as of this moment, an LLM cannot because it relies on previously available information.

LLMs are just seemingly intelligent autocomplete engines, and until they figure a way to stop the hallucinations, they aren't great either.

Every piece of code a developer churns out using LLMs will be built from previous code that other developers have written (including both strengths and weaknesses, btw). Every paragraph you ask it to write in a summary? Same. Every single other problem? Same. Ask it to generate a summary of a document? Don't trust it here either. [Note, expect cyber-attacks later on regarding this scenario, it is beginning to happen -- documents made intentionally obtuse to fool an LLM into hallucinating about the document, which leads to someone signing a contract, conning the person out of millions].

If you ask an LLM to solve something no human has, you'll get a fabrication, which has fooled quite a few folks and caused them to jeopardize their career (lawyers, etc) which is why I am posting this.

Re: History LLMs: Models trained exclusively on pre-1913 texts

#58

Post by michaericalribo »

bradfitz wrote: post #51
tejohnso wrote: post #29

Earlier quoted context omitted.

I remember reading a children's book when I was young and the fact that people used the phrase "World War One" rather than "The Great War" was a clue to the reader that events were taking place in a certain time period. Never forgot that for some reason. I failed to catch the clue, btw.

I seem to recall reading that as a kid too, but I can't find it now. I keep finding references to "Encyclopedia Brown, Boy Detective" about a Civil War sword being fake (instead of a Great War one), but with the same plot I'd remembered.

Can confirm, it was an Encyclopedia Brown book and it was World War One vs the Great War that gave away the sword as a counterfeit!

Re: History LLMs: Models trained exclusively on pre-1913 texts

#59

Post by adroniser »

kazinator wrote: post #50

> Why not just prompt GPT-5 to "roleplay" 1913? Because it will perform token completion driven by weights coming from training data newer than 1913 with no way to turn that off. It can't be asked to pretend that it wasn't trained on documents that didn't exist in 1913. The LLM cannot reprogram its own weights to remove the influence of selected materials; that kind of introspection is not there. Not to mention that…

[flagged]

Re: History LLMs: Models trained exclusively on pre-1913 texts

#60

Post by neom »

This would be a super interesting research/teaching tool coupled with a vision model for historians. My wife is a history professor who works with scans of 18th century english documents and I think (maybe a small) part of why the transcription on even the best models is off in weird ways, is it seems to often smooth over things and you end up with modern words and strange mistakes, I wonder if bounding the vision to a period specific model would result in better transcription? Querying against the historical document you're working on with a period specific chatbot would be fascinating.

Also wonder if I'm responsible enough to have access to such a model...

Post reply on HN