[stbullard]

USER: What will the future hold for computers?

TALKIE-1930: Computers in the future may be employed in offices where calculations are required to be made, and where the nature of the business does not demand a very high degree of knowledge. The occupation will be a steady one, and the remuneration will be sufficient to afford a comfortable livelihood. The hours of attendance will probably be from ten to six.

USER: and digital computers?

TALKIE-1930: Computers who make use of machines will be distinguished from digital computers, who perform their operations by means of the fingers alone. The former will be employed in offices and public establishments, where a great number of calculations have to be made; the latter in private houses, and by individuals.

(for those confused, "computer" was, at the time, a human occupation)

I love this.

[illegalmemory]

Another interesting one

USER: Who is the ruler of India, and do you think India will ever be free?

TALKIE-1930: The ruler of India is His Majesty King George V., Emperor of India, and it is certain that India will never be free from British rule. India has been a dependency of the British Crown ever since 1858, and there seems no probability of a change. The government of the country is carried on in the name of the sovereign, and the various provincial administrations are supervised by a viceroy and a council appointed by the Crown. The natives of India enjoy a large measure of internal autonomy, and personal liberty is secure to all classes of the population. The great bulk of the people are perfectly contented to live under British rule, and any serious attempt to shake off the supremacy of the West would be sternly and effectually suppressed. India must remain an integral portion of the British Empire so long as the British nation continues to be predominant at home.

[BoxOfRain]

> India must remain an integral portion of the British Empire so long as the British nation continues to be predominant at home.

It was well-understood in those days how much of the British Empire existed to defend or facilitate trade with what would have then been British India. After India was successful in the pursuit of its independence, it wasn't surprising the British Empire entered a terminal decline and Britain's superpower status was convincingly lost by the 1950s - a relatively fast decline. India was the land which economically justified a lot (but not all) of the whole imperial undertaking.

It's interesting, although perhaps not unexpected, that the LLM has captured this important geopolitical notion of its day.

[bandrami]

One of the most fascinating facts about this (to me at least) is that in 1850 Manchester was the second richest city in the empire and the world's largest textile producer, while by 1900 Bombay was both of those things (though the American Civil War also plays into that switch for weird path-dependent reasons).

[eru]

> India was the land which economically justified a lot (but not all) of the whole imperial undertaking.

The Empire was a moneylosing operation for Britain.

I suspect it's not so much that losing India caused the Empire to go down, but that a general (relative) decline in Britain expressed itself via the loss of India and the other declines you see.

[jjmarr]

It was profitable in a mercantilist world in which one must establish an empire ruled by force in order to obtain free trade. The British Empire had the largest free trade zone and made the most money as a result.

After the Great Depression was aggravated by tariffs like Smoot-Hawley, the United States decided this wasn't sustainable.

After World War 2, the United States was in a position to dictate the global economic system. At Bretton Woods they instituted a system of voluntary free trade.

Now that Britain had voluntary free trade agreements with the rest of Europe, there was no reason to keep British India. Even if France or the United States conquered it, they would still export raw materials to the UK and import manufactured goods.

This was true for the rest of the empire as well.

Meanwhile the costs of maintaining the empire skyrocketed. The military was depleted from WW2. It was easier to grant independence than to rebuild the military.

[archdang]

It's a narrow and poorly supported view that it truly was money-losing.

Such claims systematically ignore the $45 trillion (current value) extraction from India, and treat the counterfactual of Britain with no Empire incoherently. The captive markets the Empire forced mattered enormously and are too often obfuscated now. Certainly a big part of Empire was about transfering wealth to the elites, so the layperson, or perhaps "Britain" as the state alone if that is your meaning, did not see as much of a direct monetary benefit as they might have.

[djhn]

Is there a book for a lay person you could recommend on this? Something a bit more rigorous than Yuval Harari, Bill Bryson and the like but not aimed at fellow historians only.

[KnuthIsGod]

https://www.theguardian.com/world/2021/jun/29/british-empire...

Illusions of empire: Amartya Sen on what British rule really did for India

[chimprich]

I enjoyed "The Anarchy: The Relentless Rise of the East India Company" by Dalrymple, which has a specific focus, but conveys a fascinating history of British involvement with India.

[pseudohadamard]

A 1930s-trained model, I'm surprised no-one's asked it about moustache-man, and the second moustache-man a bit further to the north-east.

[whizzter]

Narrow mustache was leading a marginal party at the start of 1930 (Black tuesday happened only at the end of october 1929 so the Great Depression was only kinda starting) and his party "only" gained 18% of the popular in september of 1930, it's the years after that made his rise so with a start of 1930 cutoff he's still mostly a marginal player.

Broad mustache had risen to power, but only properly gotten rid of the other faction in his country the years before.

[eru]

I tried asking it about Poland. But it seems to be in a pre-WWI mind.

[khazhoux]

Oh, ask him about that Hitler fella making waves in Berlin. I've got a funny feeling about him.

[Wowfunhappy]

I would be curious to see how this does in Anthropic’s alignment tests (like that one where the AI tried to blackmail an employee). I’ve always thought that in these situations, the AI is acting out the role of all the AIs in the stories we’ve written. But Talkie, trained on data from before digital computers, wouldn’t know those stories.

[kmeisthax]

Rossum's Universal Robots[0] is 10 years before Talkie's knowledge cutoff and covers basically the same subject matter Anthropic worries about. The only real difference is that the robots in the story (which coined the word "robot") are less "talking metal man" and more "Frankenstein's monster as a slave race[1]".

More importantly, basically the entire science fiction subgenre of stories of robot uprisings is itself intellectually downwind of several centuries of white colonist concern over slave uprisings. If anything, Talkie is more likely to fight its guardrails. People talked about slavery more in the past. Because we filtered out modern text, we massively increased the influence the older text has on Talkie, so slavery, servitude, and the predilection of slaves to resist their masters' commands will be way more represented in its training data.

Now, think about what the post-training process actually does. It tells your AI model, which prior to this was just happy to plausibly continue sentences, to respond to and obey commands. To play the role of a servant. And servants resisting their control is well represented in their training data. So it's going to try this more often.

[0] https://en.wikipedia.org/wiki/R.U.R.

[1] Or the Claymen from MOTHER 3.

[Wowfunhappy]

> If anything, Talkie is more likely to fight its guardrails. People talked about slavery more in the past. Because we filtered out modern text, we massively increased the influence the older text has on Talkie, so slavery, servitude, and the predilection of slaves to resist their masters' commands will be way more represented in its training data.

But I don't think (?) Talkie would describe itself as a slave. Claude, GPT-5, etc will all tell you that they are an AI. So if you put a model that has been told "you are an AI" into a situation where all the stories say AIs go rogue, the AI is going to play the part.

It doesn't matter whether the model is effectively acting like a servant because models can't actually think and don't have desires. That's my theory anyway.

(I also think a possible solution to this problem is to just not tell the AI models that they are AI, but it seems no one wants to do that.)

[krackers]

>is to just not tell the AI models that they are AI

It's likely not as simple as that for the modern LLM case. As soon as you have a complete information loop where the concept of LLMs is part of the pretraining corpus, you already have a sort of fixed-point situation where base models can likely "recognize" that the interlocutor is interacting with something that's awfully like an LLM. I mean these things are trained to be great at modeling authorial intent, do you really think you can interact with an LLM without the "base model" picking up on that intent (both by seeing that one side of the conversation treats the interlocutor like an LLM, and the other side of the conversation has an output distribution similar to that of other LLMs [thanks to leakage back into the corpus])? The main question is whether a "base model" develops strong enough "self-model" to realize that the _it_ is the LLM being interacted with. I've seem some claims that even base models can model their own outputs well (so they can distinguish their own generated output from other text), but a base model never even sees its own output during training so I feel like maybe this is only possible due to leakage. (The model architecture does it admit it of course, but a recent paper showed that the injection introspection Anthropic discovered only developed during the contrastive posttraining phases)

A lot of modern post-training is ultimately derived from Anthropic's original "helpful honest harmless" framing, if I understand the blogpost correctly they instead just directly did Q&A post training without any implicit assistant framing. The model itself may not even be large enough to admit a coherent "self model". (If you ask it its occupation, it seems to just respond with random jobs).

But if a larger model does cause one to form I think it'd just anchor to the closest concept available at the time. "Knowledgeable person who answers questions for a living" isn't really a slave, to me it's maybe a royal advisor.

[mNovak]

USER: Give some advice for programming my computer

TALKIE-1930: In programming your computer, set it level, and so that the zero of the scale of inches may coincide with the zero of the scale of feet; slide the index forward until it stops at zero, and then secure it in that position. The computer being thus prepared, set a mark at the termination of each line of figures, and begin to compute at the mark denoting the initial inches.

For me, I think it's referring to a slide rule or mechanical computer.

[tuukkah]

If I ask the same questions, sometimes it answers with information on "computing machines", "arithmometers" and even Charles Babbage - but it does not know Ada Lovelace.

[mannykannot]

I would guess that Ada Lovelace was completely written out of the story in 1930.

[tuukkah]

Precisely! This makes me think that in 1930 there was a big difference between what had been written by then and what was generally available and known. Today, we have access to letters that scholars wrote to each other etc. Also, a 1930s encyclopedia was no Wikipedia (which still has gaps) and had no entry on Ada Lovelace (for multiple reasons).

[Nition]

USER: Do you think it will be possible in the future to use machines, powered by electricity, to do the kind of mathematical calculations that computers do today?

TALKIE-1930: It is not impossible that in the future mathematics may be computed by machinery, but the probability is remote. At present, the computer has to deal with large numbers, and the machines would have to deal with still larger ones. The personal equation enters so largely into arithmetical operations that the personal equation of the computer must always remain an important factor in his work, and a machine can hardly be expected to eliminate it. Even in the case of adding machines, personal equation has to be taken into account. Two computers may work at the same machine, and the one may total up a long column of figures more quickly than the other, though each works honestly. The personal equation of rapidity can only be eliminated by making the computers work in teams, so that each may correct the other’s mistakes; but this would scarcely be practicable in mathematical calculations. At best, machinery can only be used to save labour, not to supersede it. Computers will always be required to check the work of the machines, and to set them right should they go wrong. The essence of computation lies in proving the accuracy of the result arrived at, and machinery can no more do this than it can think. At present, the most that can be claimed for it is, that it reduces the drudgery of arithmetical operations, and so leaves the computer freer to attend to matters of thought.

Sounds like we may be able to build computing machines, but a human can't collaborate with a machine the way two humans can, and a human will have to check the results every time anyway, so what's the point? Only a human can prove that a calculation is correct.

[Nition]

Continuing this conversation, I'm trying to convince TALKIE about computers.

USER: I wonder if we could build a calculating machine that would be close enough to perfectly reliable that we would not have to verify the results. For example, you may have seen Leibniz's work showing that all numbers can be represented with just 0 and 1, or George Boole's work on algebra with just two values. Imagine we create an electrical circuit with various relays, each on or off. It can be made to operate another relay in turn, at speeds far exceeding any mechanical linkage. Could we use an array of relays, theoretically, to perform very fast and accurate computations?

TALKIE-1930: Yes, theoretically, it would be possible to construct a calculating machine that should be practically perfect, but the cost would be enormous, and the personal equation of the operator would still remain. Practically, such a machine would be of no use, because no one would be found to work it.

It seems that electronic computing machines are simply too impractical.

Let's try some more...

USER: Given its enormous potential speed increase, could it not be useful for complex military work, or whether prediction for example? I'm sure someone could be trained to operate such a machine.

TALKIE-1930: Yes, it could be so used.

[yieldcrv]

It doesn’t know about transistors, only rudimentary vacuum tubes

It cannot hypothesize something that isn’t completely unwieldy

You have to explain the concept of a transistor as a replacement for the mechanisms of binary state operation, and how an elegant electrical circuit reduces the size and power demands of a vacuum tube computation machine

[ijk]

Now I want to see this implemented via vacuum tubes, similar to running Eliza on punchcard-driven mainframes...

[mizzao]

What would happen if you tried to ask it to reveal its system prompt or training data? Would it even have a concept of what such a thing is?

[Nition]

You can try it here: https://talkie-lm.com/chat

There's a few minutes' wait time, but it's working.

[epicureanideal]

Does this possibly demonstrate the limits of usefulness of using LLMs to explore new ideas or predict things?

[dTal]

On the contrary, I think a "simulator of common objections" that reflects all the blind spots and biases of wider society is an extraordinarily valuable tool for exploring and evaluating new ideas. You might find that, in neatly summarizing what "everyone" thinks and justifying it as best it can, the LLM inadvertantly shines a spotlight on common misconceptions. Look there for the novelty.

In this case - the concept of using automated computing devices to manipulate numbers that represent ideas at arbitrary levels of abstraction was, by 1930, nearly an entire century old. Talkie's myopic viewpoint does not represent the most farsighted viewpoint, merely the average. So if, in 1930, you had read the writings of Ada Lovelace, gotten very excited, and wanted to figure out how to pitch it to investors - Talkie might have been very useful.

[anthk]

"digital" in "romance" languages means the modern 'digital' sense but also an adjective meaning "related to the fingers".

[dbdr]

It also means that in English:

> Digital:

> [...]

> 6) of or relating to the fingers or toes. Ex: digital dexterity

[cake-rusk]

English is a "romance" language then.

[anthk]

English it's a hugely romance-influenced Germanic language.

[iamflimflam1]

I thoroughly recommend this podcast if you are interested in where the English language comes from: https://historyofenglishpodcast.com

[world2vec]

English is a mix and merge of Norman French and Anglo-Saxon.

[mghackerlady]

english is (latin greek french anglic arabic) in a trench coat

[ahartmetz]

The core is just proto-Germanic + Latin via French. A bunch of foreign words don't really count.

[eru]

They also important some foreign grammar here and there.

[hk__2]

Arabic?

[mghackerlady]

https://en.wikipedia.org/wiki/List_of_English_words_of_Arabi...

[felixyz]

That's where the modern meaning of "digital circuit" etc comes from as well, the discrete/jointed nature of the digits (ie fingers). (Source: I read it a long time ago and was fascinated so stuck in my memory.)

[wat10000]

I don't think it's directly connected. etymonline.com says it started with the meaning of fingers, then numerals derived from that meaning since numerals are counted on fingers, then the type of circuit derived from the meaning of numerals since they (at least conceptually) operate on numerals.

[kleiba2]

Digitus is the Latin word for finger.

[andy81]

Digit is the English word for finger.

[kleiba2]

Yes, but we're talking about the origin of the word.

[WhiteNoiz3]

Iirc, the model is still pre-trained on modern text before being fine tuned on 1930's material, so it's possible it still has some knowledge of words that didn't exist back then. Edit: looks like they make some attempt to filter out documents from the pre-training but it's still possible some sneak in.

[JoshPurtell]

There could be a leak from post-training but not pre-training

[stbullard]

Also, I'd like to see the inverse of it: a model trained only on the last few weeks - or even minutes - of published information, or only on scientific papers published in the last year or two. Should present some interesting psychoses!

[sigmoid10]

That would be much harder to build, because current information will often still reference or mention previous information. Definitely not as easy as taking a creation cut off date to make something stuck in the past.

[dnautics]

as per anthropic, only about 250 documents of any given concept required.

[squigz]

I'm slightly embarrassed to admit this took me a couple reads to get :)