Live data from Hacker News

Talkie: a 13B vintage language model from 1930

talkie-lm.com

91–100 of 350 posts

Re: Talkie: a 13B vintage language model from 1930

#91

User Were there people in opposition of automatization and industrialization? And if so, what were their reasons? talkie-1930 Yes, there were people who objected to the introduction of machinery, on the ground that it would deprive the working classes of employment. It was argued that, as the new methods of production must necessarily lower the cost of articles, and so increase consumption, more would be produced tha…

I'm really enjoying the way it writes and its tone.

We're going to be able to simulate any period of time (for which we have or can simulate data) and transport ourselves there.

This is going to be amazing.

At some point I'm going to data mine all of my old internet AIM and IRC chats, emails, old laptop hard drives, essays, etc. and go nostalgia/core on it. I have old video and audio recordings too. Lots of stuff for reminiscent inference.

Every day I'm finding it harder to believe we're not already in a simulation.

Re: Talkie: a 13B vintage language model from 1930

#92
post #91

Earlier quoted context omitted.

I'm really enjoying the way it writes and its tone.

We're going to be able to simulate any period of time (for which we have or can simulate data) and transport ourselves there. This is going to be amazing. At some point I'm going to data mine all of my old internet AIM and IRC chats, emails, old laptop hard drives, essays, etc. and go nostalgia/core on it. I have old video and audio recordings too. Lots of stuff for reminiscent inference. Every day I'm finding it har…

> Every day I'm finding it harder to believe we're not already in a simulation.

Seek help before it’s too late.

Re: Talkie: a 13B vintage language model from 1930

#93
post #91

Earlier quoted context omitted.

We're going to be able to simulate any period of time (for which we have or can simulate data) and transport ourselves there. This is going to be amazing. At some point I'm going to data mine all of my old internet AIM and IRC chats, emails, old laptop hard drives, essays, etc. and go nostalgia/core on it. I have old video and audio recordings too. Lots of stuff for reminiscent inference. Every day I'm finding it har…

> Every day I'm finding it harder to believe we're not already in a simulation. Seek help before it’s too late.

Dude, I'm having a blast. I love life.

Terminally online doomerism is what needs to be reined in.

This tech is legitimately the jet packs we dreamed of as kids. It's better, even.

Re: Talkie: a 13B vintage language model from 1930

#94
post #45
post #4

I think that one could also take a much larger model (35B or 122B sized) and give it a thorough system prompt to only speak in the manner of a well educated Victorian/Edwardian era gentleman, if you want an "old timey" LLM.

It's hard to know how accurate that is. Is the LLM truly imitating text from that era, or is it imitating a modern idea of text from that era? Also, safety/alignment training would probably prevent it from embracing many of the ideas from that era, even in roleplay.

There's 'uncensored' versions of Qwen 3.6 35B at Q6 and Q8 quantization levels (somewhere from 28GB to 40GB on disk as GGUF files) out there now that won't refuse any prompt. Imitating a Victorian era person is very tame compared to what you can get it to output.

Re: Talkie: a 13B vintage language model from 1930

#95
post #67

Earlier quoted context omitted.

> and travellers will be able to go from London to Constantinople in forty hours By the 1930s, Constantinople been a long time gone. It had been Istanbul not Constantinople for centuries by that point.

That's nobody's business but the Turks. Why did Turkey become Türkiye but Japan didn't become Nippon (or vice-versa!)? It's all very confusing to me.

Turks did not really want it to become Türkiye in English, it was a government push. Most of us prefer having the name of our country be pronounceable and writable by anyone talking about it, and no one will even notice if you call it Turkey.

Re: Talkie: a 13B vintage language model from 1930

#97
post #91

Earlier quoted context omitted.

I'm really enjoying the way it writes and its tone.

We're going to be able to simulate any period of time (for which we have or can simulate data) and transport ourselves there. This is going to be amazing. At some point I'm going to data mine all of my old internet AIM and IRC chats, emails, old laptop hard drives, essays, etc. and go nostalgia/core on it. I have old video and audio recordings too. Lots of stuff for reminiscent inference. Every day I'm finding it har…

This assumes that written data from a particular time period actually reflects what it was like in that time period, and isn't highly biased to select for, say, particular socioeconomic classes.

Re: Talkie: a 13B vintage language model from 1930

#98
post #57

It seems to be using more info from pre-1900 rather than 1930. It doesn't know about the Great Depression (1929-WWII). It knows about WWI if you ask it specifically, but talks about European politics as if it's 1900 or so. On technology, it knows who Edison is, at roughly the Wikipedia level, but credits him with a 125MPH car. About a dial telephone, it is confident and totally confused. It has the traction voltage f…

Ask it about the aether as well. I think it was disproven around that time.

Re: Talkie: a 13B vintage language model from 1930

#99
post #78

Will mankind ever travel to the moon? > Yes; in the course of time, men will certainly travel to the moon. The journey will be performed in safety, and at a comparatively rapid rate. Just how fast, can not be predicted; but it will be sufficiently great to enable the voyager to make the trip in six hours. The mode of conveyance will probably be an aerial machine, similar to those in which M. Santos Dumont lately acco…

The idea of using the moon as a weather satellite is rather ingenious.

Re: Talkie: a 13B vintage language model from 1930

#100
>talkie is a 13-billion-parameter language model trained on pre-1931 text >It can produce outputs that are inaccurate or offensive >but moderation is [only] applied

I don't think you can get even a moderate version of a person's opinion from the 30's. What even is the point of this? Open any book from the time and you will get far more "current day offensive" stuff. Given how hard it is to believe that there was no temporal leaking, and how inaccurate the results are, what use is there to it?

Moderation also seems to silently hang up the chat.

Post reply on HN