History LLMs: Models trained exclusively on pre-1913 texts
1–10 of 452 posts
Re: History LLMs: Models trained exclusively on pre-1913 texts
#2smbc did a comic about this: http://smbc-comics.com/comic/copyright The punchline is that the moral and ethical norms of pre-1913 texts are not exactly compatible with modern norms.
Re: History LLMs: Models trained exclusively on pre-1913 texts
#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 and historical fiction I think this is really intriguing. Imagine having a conversation with someone genuinely from the period, where they don’t know the “end of the story”.
Re: History LLMs: Models trained exclusively on pre-1913 texts
#4The sample responses given are fascinating. It seems more difficult than normal to even tell that they were generated by an LLM, since most of us (terminally online) people have been training our brains' AI-generated text detection on output from models trained with a recent cutoff date. Some of the sample responses seem so unlike anything an LLM would say, obviously due to its apparent beliefs on certain concepts, though also perhaps less obviously due to its word choice and sentence structure making the responses feel slightly 'old-fashioned'.
Re: History LLMs: Models trained exclusively on pre-1913 texts
#5This is a neat idea. I've been wondering for a while now about using these kinds of models to compare architectures.
I'd love to see the output from different models trained on pre-1905 about special/general relativity ideas. It would be interesting to see what kind of evidence would persuade them of new kinds of science, or to see if you could have them 'prove' it be devising experiments and then giving them simulated data from the experiments to lead them along the correct sequence of steps to come to a novel (to them) conclusion.
Re: History LLMs: Models trained exclusively on pre-1913 texts
#6The sample responses given are fascinating. It seems more difficult than normal to even tell that they were generated by an LLM, since most of us (terminally online) people have been training our brains' AI-generated text detection on output from models trained with a recent cutoff date. Some of the sample responses seem so unlike anything an LLM would say, obviously due to its apparent beliefs on certain concepts, t…
The time cutoff probably matters but maybe not as much as the lack of human finetuning from places like Nigeria with somewhat foreign styles of English. I'm not really sure if there is as much of an 'obvious LLM text style' in other languages, it hasn't seemed that way in my limited attempts to speak to LLMs in languages I'm studying.
Re: History LLMs: Models trained exclusively on pre-1913 texts
#7The sample responses given are fascinating. It seems more difficult than normal to even tell that they were generated by an LLM, since most of us (terminally online) people have been training our brains' AI-generated text detection on output from models trained with a recent cutoff date. Some of the sample responses seem so unlike anything an LLM would say, obviously due to its apparent beliefs on certain concepts, t…
The time cutoff probably matters but maybe not as much as the lack of human finetuning from places like Nigeria with somewhat foreign styles of English. I'm not really sure if there is as much of an 'obvious LLM text style' in other languages, it hasn't seemed that way in my limited attempts to speak to LLMs in languages I'm studying.
There is. I have observed it in both Chinese and Japanese.
Re: History LLMs: Models trained exclusively on pre-1913 texts
#8I’d like to know how they chat-tuned it. Getting the base model is one thing, did they also make a bunch of conversations for SFT and if so how was it done?
We develop chatbots while minimizing interference with the normative judgments acquired during pretraining (“uncontaminated bootstrapping”).
Re: History LLMs: Models trained exclusively on pre-1913 texts
#9The sample responses given are fascinating. It seems more difficult than normal to even tell that they were generated by an LLM, since most of us (terminally online) people have been training our brains' AI-generated text detection on output from models trained with a recent cutoff date. Some of the sample responses seem so unlike anything an LLM would say, obviously due to its apparent beliefs on certain concepts, t…
The time cutoff probably matters but maybe not as much as the lack of human finetuning from places like Nigeria with somewhat foreign styles of English. I'm not really sure if there is as much of an 'obvious LLM text style' in other languages, it hasn't seemed that way in my limited attempts to speak to LLMs in languages I'm studying.
The model is fined tuned for chat behavior. So the style might be due to
- Fine tuning
- More Stylised text in the corpus, english evolved a lot in the last century.
Re: History LLMs: Models trained exclusively on pre-1913 texts
#10smbc did a comic about this: http://smbc-comics.com/comic/copyright The punchline is that the moral and ethical norms of pre-1913 texts are not exactly compatible with modern norms.
That's the point of this project, to have an LLM that reflects the moral and ethical norms of pre-1913 texts.