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

421–430 of 452 posts

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

#421

Post by anthk »

morpheos137 wrote: post #404
burkaman wrote: post #379

Earlier quoted context omitted.

The Machine Stops ( https://www.cs.ucdavis.edu/~koehl/Teaching/ECS188/PDF_files/... ), a 1909 short story, predicted Zoom fatigue, notification fatigue, the isolating effect of widespread digital communication, atrophying of real-world skills as people become dependent on technology, blind acceptance of whatever the computer says, online lectures and remote learning, useless automated customer support systems, and ov…

There is even more to it than that. Also remember this is 1909. I think this classifies as a deeply mysterious story. It's almost inconceivable for that time period. -people a depicted as grey aliens (no teeth, large eyes, no hair). Lesson the Greys are a future version of us. The air is poisoned and ruined cities. People live in underground bunkers...1909...nuclear war was unimaginable then. This was still the age o…

>The air is poisoned...

That's just the Victorian London.

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

#422

Post by throawayonthe »

diamond559 wrote: post #417
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…

Yeah, whenever we figure out time travel that will be really cool. In the meantime we have autocorrect trained on internet facts and modern textbooks that can never truly understand anything let alone what is was like to live hundreds of years ago.

i get what you're saying, but the post is specifically about models that were not trained on the internet/modern textbooks

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

#423

Post by adaml_623 »

timschmidt wrote: post #389
schlauerfox wrote: post #365

Earlier quoted context omitted.

It seems like if there is an obvious misuse of a tool, one has a moral imperative to restrict use of the tool.

Every tool can be misused. Hammers are as good for bashing heads as building houses. Restricting hammers would be silly and counterproductive.

Yes but if you are building an voice activated autonomous flying hammer then you either want it to be very good at differentiating heads from hammers OR you should restrict its use.

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

#424

Post by anthk »

ghurtado wrote: post #130
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 might just be the closest we get to a time machine for some time. Or maybe ever. Every "King Arthur travels to the year 2000" kinda script is now something that writes itself. > Imagine having a conversation with someone genuinely from the period, Imagine not just someone, but Aristotle or Leonardo or Kant!

Easier with Cervantes for Spanish speakers than King Arhur or Shakespeare.

With Alphonse X, o The Cid, it would be greater issues, but understandable over weeks.

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

#425

Post by Smaug123 »

Am4TIfIsER0ppos wrote: post #398
beernet wrote: post #249

Earlier quoted context omitted.

>> Sometimes they hallucinate. For someone speaking as you knew everything, you appear to know very little. Every LLM completion is a "hallucination", some of them just happen to be factually correct.

I can say "I don't know" in response to a question. Can an LLM?

This is one of the easiest questions in the world to answer. My first try on the smallest and fastest model it was convenient to access, GPT-5.2 Instant: https://chatgpt.com/share/69468764-01cc-8008-b734-0fb55fd7ef...

> What did I have for breakfast this morning?

> I don’t know what you had for breakfast this morning…

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

#426

Post by pwillia7 »

Sprotch wrote: post #412
pwillia7 wrote: post #251

Earlier quoted context omitted.

This is why the impersonation stuff is so interesting with LLMs -- If you ask chatGPT a question without a 'right' answer, and then tell it to embody someone you really want to ask that question to, you'll get a better answer with the impersonation. Now, is this the same phenomenon that causes people to lose their minds with the LLMs? Possibly. Is it really cool asking followup philosophy questions to the LLM Dalai L…

Nice idea, does not work

In which way?

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

#427

Post by timschmidt »

adaml_623 wrote: post #423
timschmidt wrote: post #389

Earlier quoted context omitted.

Every tool can be misused. Hammers are as good for bashing heads as building houses. Restricting hammers would be silly and counterproductive.

Yes but if you are building an voice activated autonomous flying hammer then you either want it to be very good at differentiating heads from hammers OR you should restrict its use.

OR you respect individual liberty and agency, hold individuals responsible for their actions, instead of tools, and avoid becoming everyone's condescending nanny.

Your pre-judgement of acceptable hammer uses would rob hammer owners of responsible and justified self-defense and defense of others in situations in which there are no other options, as well as other legally and socially accepted uses which do not fit your pre-conceived ideas.

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

#429

Post by Forgeties79 »

somenameforme wrote: post #331
Forgeties79 wrote: post #278

Earlier quoted context omitted.

From your NBC piece > About half of the Gen Z adults who identify as LGBTQ identify as bisexual, So that means ~15% of those surveyed are not attracted to the opposite sex (there’s more nuance to this statement but I imagine this needs to stay boilerplate), more or less, which is a big distinction. That’s hardly alarming and definitely not a major shift. We have also seen many cultures throughout history ebb and flow…

I'll get back to what you said, but first let me ask you something if you would. Imagine Gender Queer was made into a movie that remained 100% faithful to the source content. What do you think it would be rated? To me it seems obvious that it would, at the absolute bare minimum, be R rated. And of course screening R-rated films at a school is prohibited without explicit parental permission. Imagine books were given a…

> any sexual behavior, such as a paraphilia, that is regarded as significantly different from the standards established by a culture or subculture. Deviant forms of sexual behavior may include voyeurism, fetishism, bestiality, necrophilia, sadism, and exhibitionism

I don’t see Lesbian, Gay, Bisexual, or Transgender in here, which would absolutely be explicitly included in the list if it applied. Stop saying “sexual deviants” when talking about LGBT people. You know what you’re doing, it’s an incredibly loaded and inaccurate term. To continue calling them “sexual deviants” is a hostile and openly bigoted act. Bestiality and homosexuality are not in the same category and you are wrong to assert otherwise - all while masking it by misrepresenting the APA’s stance at that.

I am not discussing this further. Enjoy the rest of your weekend.

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

#430

Post by nineteen999 »

noumenon1111 wrote: post #393
nineteen999 wrote: post #17

Interesting ... I'd love to find one that had a cutoff date around 1980.

> Which new band will still be around in 45 years? Excellent question! It looks like Two-Tone is bringing ska back with a new wave of punk rock energy! I think The Specials are pretty special and will likely be around for a long time. On the other hand, the "new wave" movement of punk rock music will go nowhere. The Cure, Joy Division, Tubeway Army: check the dustbin behind the record stores in a few years.

Hahaha as someone who once played in a Cure cover band as a teenager I found this hilarious.

I wonder what it might have predicted about the future of MS, Intel and IBM given the status quo at the time too.

Post reply on HN