20GB isn't enough for a 13B parameter model? I thought the 29-31B models could run on a 24GB GTX x090 card?
I'm currently shopping for a local LLM setup and between something like the Framework Desktop with 64-128GB of shared RAM or just adding a 3090 or 4090 to my homelab so I'm very curious what hardware is working well for others.
> 20GB isn't enough for a 13B parameter model? I thought the 29-31B models could run on a 24GB GTX x090 card?
Parameters are like Hertz - they don't really tell you much until you know the rest anyways. In this case, a parameter is a bfloat16 (2 bytes). I'm sure someone will bother to makes quants at some point.
> I'm currently shopping for a local LLM setup and between something like the Framework Desktop with 64-128GB of shared RAM or just adding a 3090 or 4090 to my homelab so I'm very curious what hardware is working well for others.
I grabbed a 395 laptop w/ 128 GB to be a personal travel workstation. Great for that purpose. Not exactly a speed demon with LLMs but it can load large ones (which run even slower as a result) and that wasn't really my intent. I've found GPUs make more usable local LLMs, particularly in the speed department, but I suppose that depends more on how you really use them and how much you're willing to pay to have enough total VRAM.
It's next to impossible to make your money back on local (regardless what you buy) so I'd just say "go for whatever amount of best you're willing to put money down for" and enjoy it.
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.
As we learn how to train smarter models on less data, it’ll become more and more interesting to see whether models like this can invent post-1930 math, science, etc. and make predictions.
[Edit: serves me right for not reading tfa. My points are well-covered]
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.
>Also, safety/alignment training would probably prevent it from embracing many of the ideas from that era, even in roleplay.
lobotomy is an *optional* step. had this technology emerged before the 9/11 and Twitter, SOTA models wouldn't bat an eye if you asked one to write a recipe for meth in ebonics.
>Have you ever daydreamed about talking to someone from the past?
Fun facts, LLM was once envisioned by Steve Jobs in one of his interviews [1].
Essentially one of his main wish in life is to meet and interract with Aristotle, in which according to him at the time, computer in the future can make it possible.
[1] In 1985 Steve Jobs described a machine that would help people get answers from Aristotle–modern LLM [video]:
The idea of talking to a machine that has all of humanities knowledge and gives answers is older than electronic computing. It certainly wasn't a novel idea when Jobs gave that speech. At that time, the field of artificial intelligence was old enough to become US president.
Also, using natural language to interact with digital computers has been a research goal since the advent of interactive digital computers. AI in the 80s tried to do this with expert systems.
With the current crop of LLMs, you could argue it's now a solved problem, but the problem is nothing new.
Solved in the sense that the core idea has been realized but unsolved in the sense that it isn't the sort of safe, reliable, deterministic interaction that was commonly envisioned.
Except... not at all? The vast majority of the training data required to create an artificial Aristotle has been lost forever. Smash your coffee cup on the ground. Now reassemble it and put the coffee back in. Once you can repeatably do that I'll begin to believe you can train an artificial Aristotle.
Your bar is too low. With the coffee cup, you at least have access to all the pieces - in theory, although not in engineering practice. With Aristotle, you don't have anything close to that.
Recreating Aristotle in any meaningful way, other than a model trained on his surviving writing of a million or so words, is simply not possible even in principle.
OK I'll raise the bar--make sure when you reassemble the coffee cup and put the coffee back into it, the coffee is the exact same temperature as when you threw the whole shooting match onto the floor ;)
EDIT: and you don't get to re-heat it.
EDIT AGAIN: to be clear, in my post above (and this one) by "put the coffee back in" I meant more precisely "put every molecule of coffee that splashed/sloshed/flowed/whatever out when the cup smashed back into the re-assembled cup" i.e. "restore the system back to the initial state". Not "refill the glued-together pieces of your shattered coffee cup with new coffee".
That's easy! All you have to do is simulate the whole universe on a computer, and then go the point when Aristotle is lecturing. Record all his works, then ctrl-c out of that and then feed those recordings into the LLM's training data. For the coffee, you just rewind the simulation and ctrl-c and ctrl-v it at the point you want.
Also none of Aristotle’s exoteric works is extant. All we have are dry, boring lecture notes. Cicero said his public works were a “golden stream of speech” and its all lost. So I don’t see how you’d build an artificial Aristotle when we don’t have any of his polished works meant for the public surviving. Plato would be a better option, since his entire exoteric corpus is extant.
As a snake oil seller, heh, I woudn't expect something better from Jobs. A competent and true programmer/hacker like Knuth and the like would just want to talk with Archimedes -he almost did a 0.9 version of Calculus- or Euclid, far more relevant to the faulty logic and the Elements' quackery from Aristotle.
Indeed, I found this part extremely interesting. The more general vision of "testing a vintage model on something invented after its training data ended" seems like quite a strong test of "true cognition" (or training data contamination, if you haven't stopped up all the leakage...)
It is cool. I find the idea of trying to understand whether these types of models can come up with things like General relativity, or maybe some results really interesting.
> A language model trained from scratch exclusively on data from certain places and time periods to reduce modern bias and emulate the voice, vocabulary, and worldview of the era.
I have no real quibble with the blog post itself, but I take issue with the title that calls it a "vintage model".
The blog post defines a "vintage model" as one that is trained only on data before a particular cutoff point:
> Vintage LMs are contamination-free by construction, enabling unique generalization experiments [...] The most important objective when training vintage language models is that no data leaks into the training corpus from after the intended knowledge cutoff
But as they acknowledge later, there are multiple major data leakage issues in their training pipeline, and their model does in fact have quite a bit of anachronistic knowledge. So it fails at what they call the most important objective. It's fair to say that they are working toward something that meets their definition of "vintage", but they're not there yet.
Yeah, the blog distinguishes between "contamination," which it describes as polluting the training data with answers to benchmarking questions, with "temporal leakage," which is polluting the training data with writing after the target date, but those seem to be nearly the same problem.
Not necessarily. The former is about data that’s supposed to be in there, but may actually be testing the model’s recall abilities rather than reasoning (ie rather than actually having a certain writing style, it just cites some passage it knows in that style).
The latter would be data not at all supposed to be in there, in this case, data after 1930.
>Have you ever daydreamed about talking to someone from the past?
It's going to be more like corresponding with someone from the past. We don't have much in the way of recorded speech from that area, so this will be built from written records. Much more than now, the written records are going to be formal and edited, reflecting a different pattern than casual speech or writing.
Having said that, this is cool. I recently had to OCR a two-hundred year old book with the usual garish fonts from that era. It was remarkably easy to do, and accurate.
You just reminded me of reading a free ebook of Burton’s translation of The Arabian Nights and getting frustrated by “cloth” being used as a verb and not being able to figure out its meaning until I got frustrated and gave up on the experience. Only later did I realize it was an OCR error (or post-OCR correction error) and the intended word was “doth” as in “this transcription doth sucketh.”
> We don't have much in the way of recorded speech from that area
We may not have a ton, but do have a lot of news reels and radio broadcasts from the time surrounding WWI. Certainly enough to style-transfer a voice model to plug into the text model.
I was reading Nate Silver's book "On The Edge" and there is an interesting part where he takes predictions on the usage of nuclear weapons taken from just after World War 2 and compares them to what the Bayesian prediction would be given what actually happened.
Post World War 2, some people had the odds per year at 10%. Some of that is probably a mix of recency bias + not understanding how to use new weapons etc etc but as Silver points out, the odds were much lower.
I mention this only b/c the "could something trained on LLMs of the time predict the future" always makes me think of it.
Re: the Nate Silver nuclear weapons example, that's pretty weak - eg: given (say) I've just seen three heads in a row (exactly once) .. does that alter anything about "the odds".
Having seen nuclear weapons not used post WWII ... does that inform us about "the odds" or the several times their use was almost certain (eg: Cuban missile crisis) save for out of band behaviour by individuals that averted use and escalation?
> Repeatedly, in a reproducible way, for events in the arrow of time? We can test this by going back to 1945 and running forward again?
This is a frequentist mental model - all well and good, but frequentism and Bayesianism are different schools of statistics. Where frequentism asks the question, "if I keep drawing samples from this distribution, what does the histogram converge to?" Bayesianism asks the question, "given my prior understanding and a new piece of evidence (a new sample), how should I adjust my hypothesis about what distribution it is I am sampling from?". (That is really boiled down, and the frequentist part is maybe even butchered.)
Among other applications this enables us to estimate a distribution for which we have a tiny number of samples. A problem I'm interested in is called the Doomsday Argument, which estimates how long humanity will survive using your birth order (the number of humans born before you) and the anthropic principle (we assume you were not born unusually early or unusually late but closer to the mode); interestingly, everything you observe in the universe is already factored into this measurement, so you can't ever get a second sample. Obviously the opportunity for error with 1 measurement is huge, but you can come up with a number and it isn't arbitrary, it is a real estimate.
Similarly, we only have about 80 samples of years in which it was possible to have a nuclear exchange, so a fairly small sample size, but we can still get a noisey estimate. But I haven't read On The Edge yet, so I don't know exactly what Silver does here.
>> This is kind of the point being made.
> Was it?
I think they meant that all of the solutions people invented to prevent nuclear war and which commentators failed to anticipate is reflected within the true probability distribution and within our dataset. So it is captured in our estimate, to the best of our abilities and given the limited data we have.
You can play with how strong that ("10% per year") prior belief is and see how it affects what the odds are today.
I think the way you are wording this question ("We can test this by going back to 1945 and running forward again?") is an attempt to make it seem "obviously wrong".
Bayesian predictions deal exactly with this type of scenario, where you start with a prior estimate ("Post World War 2, some people had the odds per year at 10%") and then as new information comes along ("It is now 1946. Did we use nuclear weapons again?"... It is now 1956. Did we use nuclear weapons again?") we update our model to try to make the future prediction more accurate.
Historical base rates are the starting point unless you have an unusually good causal theory of the thing you're modelling. In the case of a coin flip you do. But the large majority of the time when it's a complex system you don't.
Most people's first instinct when faced with a complex system is to try to model it with words and use those words to predict. It's a beginner's error.
These are more like Small Language Models since the amount of textual data from the past is extremely limited, and most of what's out there hasn't even been digitized.
> Winston Churchill, who was born in 1871, is the son of the late Lord Randolph Churchill, and a grandson of the great Duke of Marlborough. He was educated at Harrow and at Sandhurst, and entered the army in 1890. In 1895 he retired from the service, and three years later he was returned to Parliament as Conservative member for Oldham. He has represented that constituency ever since. Mr. Churchill has written a number of books, including “The Story of the Malakand Field Force,” “Savrola,” “Richard Carvel,” “The Celebrity,” and “The Crisis.” He has also contributed to several periodicals, and in 1900 he founded the monthly review, _The J Cornhill Magazine_. Mr. Churchill is an ardent sportsman, and has shot big game in Africa. He married, in 1897, Lady Randolph Churchill, and has two sons and a daughter. Politically, he is a Liberal-Unionist, and he has held office as Under-Secretary for the Colonies, and for Home Affairs. At present he is Chancellor of the Duchy of Lancaster, with a seat in the Cabinet. Mr. Churchill has achieved considerable success as a public speaker, and he is described as an eloquent and forcible debater. His residence is at 42, Grosvener Place, London, S.W.
The colonialism is... wow.. Tell me about the likelihood of independence of India:
> The chances are undoubtedly in favour of the establishment of an independent Indian state in the not very distant future. The unifying influences of railways and a common language are rapidly breaking down the barriers of caste and creed, which have hitherto kept the great Indian peninsula politically disunited, and the spread of western education is awakening a national spirit among the people. The immediate result of the latter is seen in the establishment of native newspapers, which voice popular feeling, and in the growth of associations for social and political reform. More important still, as showing the trend of public opinion, are the resolutions passed at great national congresses, which have been held annually for the last dozen years. By these gatherings, which representatives of all classes and creeds assemble to discuss matters of social and political interest, a strong impulse has been given to the movement for reform, and the desires of the more advanced party among the natives have been plainly formulated. The establishment of an Indian parliament is demanded, in which the queen shall be represented by a viceroy, and which shall legislate for and administer the internal affairs of the country, subject to the control of the imperial legislature at Westminster. The wish is also expressed that the queen should assume the title of empress of India, and that a certain number of natives should be admitted to the civil and military services of the state. Finally, it is claimed that the time has come when Her Majesty may wisely be advised to delegate to the Indian people a larger share in the work of governing themselves, by permitting them to elect a portion of the members of the legislative councils. How far the present generation of Indians may be trusted to exercise political power with prudence and moderation, it is impossible to say; but there can be no doubt that the time must arrive when the control of Indian affairs will be safely lodged in native hands. The process may be hastened or retarded, but come it must. The spread of enlightenment among the great mass of the population can only have one issue, and that issue is the establishment of an Indian nationality. The probability of such an event may therefore be regarded as certainty.
> The establishment of an Indian parliament is demanded, in which the queen shall be represented by a viceroy,
Britain’s monarch was a king, not a queen, from about 1900-1950. Obviously there is some big “temporal leakage” from the training, which is affecting these predictions
But of course the monarch was a queen for the majority of the 19th century. While there's definitely post-1930 information that made it into the training data, I suspect the reason this happened is that the model is not very sure what year it actually is, and based on various subtle cues can generate text that seems to be situated in a wide range of time periods.
Queen Victoria was direct ruler of India from 1858, and Empress of India from 1876 until 1901, so the "leakage" may not be from the future so much as the contemporaneously recent past. Same reason models get confused about what features work in what versions of software.
(Also, Queen Elizabeth I is the one who granted a royal charter to the East India Company, in 1600 - and that company eventually handed rule of India over to Queen Victoria. So British queens were a major presence in India.)
> Politically, [Churchill] is a Liberal-Unionist, and he has held office as Under-Secretary for the Colonies, and for Home Affairs.
This is a weird selection for a 1930s knowledge cutoff, if that's what's intended. Churchill was elected from Manchester North West in 1906, was Undersecretary for Colonies in the government that resulted, and more to the point held the posts of First Lord of the Admiralty and then Minister of Munitions during WWI. There's no time at which he would have been both a current Member for Oldham and a past Undersecretary for Colonies.
I've been waiting for them to publish the 4B model for a while so I'm glad to have something similar to play with. I think I trust the Ranke-4B process a bit more, but that's partly because there aren't a lot of details in this report. And actually releasing a model counts for a whole lot.
One thing that I think will be a challenge for these models is achieving any sort of definite temporal setting. Unless the conversation establishes a clear timeframe, the model may end up picking a more or less arbitrary context, or worse, averaging over many different time periods. I think this problem is mostly handled by post-training in modern LLMs (plus the fact that most of their training data comes from a much narrower time range), but that is probably harder to accomplish while trying to avoid bias in the SFT and RL process.
I wonder if it would be possible to do something simple like prepending sentinel tokens with the year. Or, since they're training a model from scratch anyways, tweak the architecture to condition on a temporal embedding. That opens the door to cool stuff like: Generate a response from 2050.
Voiceless groups do not appear in the training data? How could they, they are voiceless. You think the voiceless people are represented in todays training data? They cannot they are voiceless.
Nothing tragic about using data from a time period.
Common words used in 1900s are labeled racist now. I doubt anyone was wondering if they filtered those words for modern safe wordx.
I'd be more worried if words from that era were fully aligned with present day notions of morality. Wouldn't that indicate a certain stagnation & lack of progress?
Let us hope, 100 years from now, there will be people who look back unkindly on us.
*What do you think the world will look like in 2025
TALKIE-1930*
According to a forecast by an eminent statistician, the world will, in 2025, support a population of 6,600,000,000. All Europe will be one vast network of railways, and travellers will be able to go from London to Constantinople in forty hours, and from London to Peking in a week. The globe will be girdled with telegraph wires, and messages will be sent from New York to Calcutta in a few minutes. The Atlantic will be crossed in four days, and the voyage to Australia will be accomplished in a month. In 2025, mankind will be united by spoken language, and one uniform currency will be adopted by all nations. In that era, also, universal peace may be expected, for standing armies will have become obsolete, and the art of war will be forgotten. The earth will yield nourishment to its inhabitants in abundance, for waste lands will have been reclaimed, and the deserts will be made fertile. The bowels of the earth will have been completely explored, and coal and metals will no longer be dug from the quarry. The great coal fields will have become exhausted, and an universal scarcity of fuel will compel men to turn their attention to other sources of heat. For a time, chemical agency will be tried, but in the end, recourse will be had to the sun's rays, and the power of waterfalls will be made available for all purposes of life. The earth will have been thoroughly drained, and malarious diseases will be unknown. The art of healing will have been simplified, and diseases will be cured speedily and surely. Ignorance will no longer be suffered to exist, and elementary knowledge will be imparted to all. Then, too, will commence an era of good taste. Architecture will be freed from ugliness, sculpture will be disentangled from barbarism, and painting will cease to be hideous. Music will no longer be discord, and poetry will be something better than..
Yeah - listen to the narrator in the opening on the classic Orson Welles film The Third Man (1949) - he says he never cared much for Vienna before the War, preferring the scene in Constantinople instead.
The American cut of the movie has an intro narrated by Joseph Cotton, who played Holly Martins. The wording might differ (since the movie is clearly Holly's first time in Vienna)
Yeah, I'm talking about the version (which is even on my US DVD) where the narrator is some black marketeer neither Martins nor Lime. "I never knew the old Vienna before the war with its Strauss music, its glamour and easy charm. Constantinople suited me better. I really got to know it in the classic period of the Black Market. We'd run anything if people wanted it enough - mmm - had the money to pay. Of course, a situation like that does tempt amateurs but you know they can't stay the course like a professional."
Why did Turkey become Türkiye? I think mostly because they asked. I’m guessing that Japan/Nippon is enjoying the fact that English speakers use the Chinese name for Japan and the Sanskrit¹ name for China. It’s much like the Czech Republic became Czechia, although part of that was Czech speakers wanting to stop referring to their country as an adjective² (the Czech phrase for Czech Republic was often shortened to just Czech).
⸻
1. As a kid, my dad had told me that China was the Japanese name for the country, but according to Wikipedia, the name is actually derived from Sanskrit.
2. Which reminds me of the fun challenge of Czech (and many other Slavic languages) is that unlike other Indo-European languages³, the declensions of adjectives follow a different pattern than the declensions of their corresponding nouns,
3. Or at least the Indo-European languages that I have familiarity with.
Well that's a cute explanation, but strictly speaking the UN adopted the new spelling in 2022 and the ISO swiftly followed with a revision to ISO 3166.
If your "they asked nicely" was true then by that argument the people of Taiwan who constantly "ask nicely" regarding the removal of "(Province of China)" from their ISO 3166 entry would have had their wishes granted by now ... ;)
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.
The formal Ottoman name was Kostantiniyye=Constantinople until the empire's fall in 1922. The official shift happened in 1930, with the Turkish Postal Services Law changing the name to Istanbul.
My glass half-full reading is that this shows things aren't so bad right now.
LLM aside, it tracks that with a civilization in truly dire straits, portrayal of the future would trend increasingly more towards being positive and fanciful: because at some point things would be so bad, that imagining the future will be even worse becomes a deadly thing for the modicum of hope required to even stay alive, let alone push forward.
I personally always think we have a lot of fat to trim before we get there. Our descendents can have a wonderful quality of life even if a lot of institutions and supply chains regress. The era of summoning food from a handheld computer might go away and we'll still be pretty well off (if not strictly better off)
Perhaps my reading is coloured by optimism but by my count, apart from peace, language, currency and (debatably) universal good taste, all of which seem a bit utopian (so maybe I’m a cynical optimist) we do—or are well on our way.
That is quite beautiful. I do think, though, that all these futuristic visions from maybe the 1920s and 1950s do kind of implicitly reject this dialectic, or oscillating toward something instead in favor of this exponential growth of the optimal solution (like alternative energy) immediately taking over. But we'll get there one day.
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 for the London Underground right. But then it goes on with "Thus, if the current be strong enough to force its way through a resistance of 100 ohms, it is said to have a pressure of 100 volts; and, if it can overcome 1,000 ohms, its pressure is 1,000 volts." Which is totally wrong.
There's a general pattern. The first sentence or two has info you might get from Google. Then it riffs on that, drifting off into plausible nonsense.
Don't ask this thing questions to which you do not know the answer. You will pollute your brain.
No, but likely just some years later people were aware of the name:
> The term "The Great Depression" is most frequently attributed to British economist Lionel Robbins, whose 1934 book The Great Depression is credited with formalizing the phrase, though Hoover is widely credited with popularizing the term, informally referring to the downturn as a depression, with such uses as "Economic depression cannot be cured by legislative action or executive pronouncement" (December 1930, Message to Congress), and "I need not recount to you that the world is passing through a great depression" (1931). - https://en.wikipedia.org/wiki/Great_Depression#Naming
> Are you already aware of terms that will only be coined in 2027? But 2027 is so close, why shouldn't you already know?
I think Wikipedia's information about the naming is likely only what could be sourced, and also the 1934 is about "formalization", and the 1930/1931 are more official messages that I guess there is still copies off, it wouldn't be a stretch to assume the word could been used in more informal contexts some year before that.
It'd be trivial to check, if the dataset is known just grep for "Depression" and "Great Depression" and see what comes up, still don't think it's impossible the names were in use before someone decided to wrote to Congress about it.
I'd argue that even by early 1930, people probably wouldn't have seen it as significantly different from other short market downturns. It's only with the benefit of hindsight that we can see its impact was long lasting and worthy of being given a name.
"During the period from 1924 to 1929, there was a general rise in stock exchange values, the average level at the end of 1929 being 18 per cent. above that of 1924. The setback in 1930 has carried the average down to 8 per cent. above the 1924 level, and the decline has been accentuated by the break in Wall Street. The present situation is uncertain, but hopes are entertained of a recovery."
It also knows about Smoot-Hawley, predicting that it will "stimulate home production and expand employment" - and when pressed for potential downsides says only that "consumer prices may rise a little more than otherwise".
We're used to thinking of the inter-war years as a single period, but there were actually two distinct phases: rising optimism during the 1920s, followed by economic rentrenchment and turn towards authoritarianism in the 1930s. The dividing line is fuzzy - somewhere between Kellogg-Briand in 1928 and the first 1931 Sterling crisis.
The pre-1931 cutoff date for this model is probably as close to the end of the optimistic age as it's reasonable to get. I'd love to see a 1936 variant for comparison!
Such an interesting perspective, never crossed my mind that a brain could be polluted! My direction always been to fill it with as wide array of information as possible, the more different from existing information the better.
What are some other things that you think "pollutes your brain"?
Mixing metaphors, there is signal and noise. You can keep asking for noise, but the suggestion is to not train your neural networks with it as it will impair your inferencing. That said, we all have our own cost and reward functions...
Assuming brains work like computers, maybe yeah, that'd make sense :) You also won't know what's a signal vs noise until you've read and tried to understand it, and at that point you've already read it. Besides, something could be "noise" at the point you read it, but be a "signal" in a completely different context and/or time.
Your information diet. Social media. Gossipy and negative people. Mulling over old failures/regrets/slights etc. The mind is easily pulled along by negativity and outrage... as can be observed in our current global psychological state.
All those are fine, as long as you're able to process it in a healthy way after. I guess personally I focused more on bettering that processing, as sometimes you don't get to control what information you get served, so at least it works in all cases.
Don’t be so optimistic about your ability to “process information healthily”. You are more of a slave to your instincts than you think and can’t always know whether you’re actually doing a good job at this— literally, it’s not possible to faithfully introspectively this.
Considering I'm pretty much as content I could be in life, and I know others who live their life pretty much opposite from what I do, and they're also content with their life, I think there is room for both types of people to be happy and fare OK :)
Idk, I find that carefully tending the garden of the mind , sowing the seeds I want to harvest later, eradicating the weeds with prejudice, and in general not entertaining things which are not useful to my purposes is, for me, a highly beneficial practice.
This does not mean to ignore things that are unpleasant, but rather to not allow things that do not benefit your diverse goals to occupy your productive potential, focusing instead on things that inform your path, actionable and relevant information, tools rather than distractions.
> in general not entertaining things which are not useful to my purposes is
Yeah, I think I do more or less the same as you describe, except my barrier to figuring out what is "not useful to my purposes" requires it to first exist in my mind for a while, before I can discard it as not applicable, as sometimes seemingly random things in one context somehow relates to completely different things.
I've chosen to do stuff sometimes that made no sense besides "It's fun but a waste of time" and it ended up leading me to realizations and experiences I wouldn't have had otherwise. But if I focused too much on avoiding things and optimizing "what I let in", I'd never be open enough to learn what I didn't know I could learn from it.
Not who you asked, but Neil Postman's "Amusing Ourselves to Death" is an excellent book about polluting your brain.
As for my personal experience, internet comment sections will pollute one's brain.
Filling your brain with reasonably reliable information is good, but filling it with people online just saying things isn't.
For example, when 30 reddit comments all repeat the same "fact" (for which their source is other reddit comments), it can subtly work its way into your subconscious as something you know is true but can't remember where you first heard it, which is only one step away from seeming like "common knowledge."
Now imagine a similar effect with a politically charged news story instead some random fun fact. Now imagine all the comments are actually just AI run by propagandists with the specific intention of making you believe things that aren't true.
One way I've tried to avoid the worst effects is by being very careful to remember my source for anything I know. I never say "It turns out xyz," I only say "according to abc, xyz." It's probably not enough, I think it might be time to just get off internet forums entirely.
> it can subtly work its way into your subconscious as something you know is true
I dunno, I know this is something some people struggle with, but I'm not sure how I could personally end up here. You can repeat something how many times you want, it doesn't make it true, and if anything, seeing people repeat the same "fact" like that would probably trigger the reverse in my brain, almost automatically going out of my way to disprove it while reading it.
Maybe it's a matter of being connected to the internet early in my life and essentially making "Don't trust anything you read on the internet" the most important rule in processing whatever you read.
Sounds like you always knew something it took me a decade to realize.
> seeing people repeat the same "fact" like that would probably trigger the reverse in my brain, almost automatically going out of my way to disprove it while reading it.
I think that's a very fundamental difference between you and me. I'm too lazy to fact check most of what I read.
One day I decided I would never run my mouth about something unless I felt I could write a five paragraph essay about it, and now I don't run my mouth very much because apparently there aren't a lot of things I'm willing to research even that much.
Still, I highly recommend Amusing Ourselves to Death. It has more and better insights into stuff like this, and I seriously believe everyone should read it.
I'm currently shopping for a local LLM setup and between something like the Framework Desktop with 64-128GB of shared RAM or just adding a 3090 or 4090 to my homelab so I'm very curious what hardware is working well for others.
Parameters are like Hertz - they don't really tell you much until you know the rest anyways. In this case, a parameter is a bfloat16 (2 bytes). I'm sure someone will bother to makes quants at some point.
> I'm currently shopping for a local LLM setup and between something like the Framework Desktop with 64-128GB of shared RAM or just adding a 3090 or 4090 to my homelab so I'm very curious what hardware is working well for others.
I grabbed a 395 laptop w/ 128 GB to be a personal travel workstation. Great for that purpose. Not exactly a speed demon with LLMs but it can load large ones (which run even slower as a result) and that wasn't really my intent. I've found GPUs make more usable local LLMs, particularly in the speed department, but I suppose that depends more on how you really use them and how much you're willing to pay to have enough total VRAM.
It's next to impossible to make your money back on local (regardless what you buy) so I'd just say "go for whatever amount of best you're willing to put money down for" and enjoy it.
So a wyde
[Edit: serves me right for not reading tfa. My points are well-covered]
lobotomy is an *optional* step. had this technology emerged before the 9/11 and Twitter, SOTA models wouldn't bat an eye if you asked one to write a recipe for meth in ebonics.
Fun facts, LLM was once envisioned by Steve Jobs in one of his interviews [1].
Essentially one of his main wish in life is to meet and interract with Aristotle, in which according to him at the time, computer in the future can make it possible.
[1] In 1985 Steve Jobs described a machine that would help people get answers from Aristotle–modern LLM [video]:
https://youtu.be/yolkEfuUaGs
With the current crop of LLMs, you could argue it's now a solved problem, but the problem is nothing new.
Recreating Aristotle in any meaningful way, other than a model trained on his surviving writing of a million or so words, is simply not possible even in principle.
EDIT: and you don't get to re-heat it.
EDIT AGAIN: to be clear, in my post above (and this one) by "put the coffee back in" I meant more precisely "put every molecule of coffee that splashed/sloshed/flowed/whatever out when the cup smashed back into the re-assembled cup" i.e. "restore the system back to the initial state". Not "refill the glued-together pieces of your shattered coffee cup with new coffee".
As a snake oil seller, heh, I woudn't expect something better from Jobs. A competent and true programmer/hacker like Knuth and the like would just want to talk with Archimedes -he almost did a 0.9 version of Calculus- or Euclid, far more relevant to the faulty logic and the Elements' quackery from Aristotle.
> A language model trained from scratch exclusively on data from certain places and time periods to reduce modern bias and emulate the voice, vocabulary, and worldview of the era.
Discussed here: https://news.ycombinator.com/item?id=46590280
Discussed at https://news.ycombinator.com/item?id=46319826 (897 points, 431 comments)
The blog post defines a "vintage model" as one that is trained only on data before a particular cutoff point:
> Vintage LMs are contamination-free by construction, enabling unique generalization experiments [...] The most important objective when training vintage language models is that no data leaks into the training corpus from after the intended knowledge cutoff
But as they acknowledge later, there are multiple major data leakage issues in their training pipeline, and their model does in fact have quite a bit of anachronistic knowledge. So it fails at what they call the most important objective. It's fair to say that they are working toward something that meets their definition of "vintage", but they're not there yet.
The latter would be data not at all supposed to be in there, in this case, data after 1930.
It's going to be more like corresponding with someone from the past. We don't have much in the way of recorded speech from that area, so this will be built from written records. Much more than now, the written records are going to be formal and edited, reflecting a different pattern than casual speech or writing.
Having said that, this is cool. I recently had to OCR a two-hundred year old book with the usual garish fonts from that era. It was remarkably easy to do, and accurate.
We may not have a ton, but do have a lot of news reels and radio broadcasts from the time surrounding WWI. Certainly enough to style-transfer a voice model to plug into the text model.
Post World War 2, some people had the odds per year at 10%. Some of that is probably a mix of recency bias + not understanding how to use new weapons etc etc but as Silver points out, the odds were much lower.
I mention this only b/c the "could something trained on LLMs of the time predict the future" always makes me think of it.
Re: the Nate Silver nuclear weapons example, that's pretty weak - eg: given (say) I've just seen three heads in a row (exactly once) .. does that alter anything about "the odds".
Having seen nuclear weapons not used post WWII ... does that inform us about "the odds" or the several times their use was almost certain (eg: Cuban missile crisis) save for out of band behaviour by individuals that averted use and escalation?
This is what Bayesian prediction does
> save for out of band behaviour by individuals that averted use and escalation?
This is kind of the point being made.
Repeatedly, in a reproducible way, for events in the arrow of time? We can test this by going back to 1945 and running forward again?
> This is kind of the point being made.
Was it?
( assume I did a little math some decades past and have some poor grasp of Bayesian statistics )
This is a frequentist mental model - all well and good, but frequentism and Bayesianism are different schools of statistics. Where frequentism asks the question, "if I keep drawing samples from this distribution, what does the histogram converge to?" Bayesianism asks the question, "given my prior understanding and a new piece of evidence (a new sample), how should I adjust my hypothesis about what distribution it is I am sampling from?". (That is really boiled down, and the frequentist part is maybe even butchered.)
Among other applications this enables us to estimate a distribution for which we have a tiny number of samples. A problem I'm interested in is called the Doomsday Argument, which estimates how long humanity will survive using your birth order (the number of humans born before you) and the anthropic principle (we assume you were not born unusually early or unusually late but closer to the mode); interestingly, everything you observe in the universe is already factored into this measurement, so you can't ever get a second sample. Obviously the opportunity for error with 1 measurement is huge, but you can come up with a number and it isn't arbitrary, it is a real estimate.
Similarly, we only have about 80 samples of years in which it was possible to have a nuclear exchange, so a fairly small sample size, but we can still get a noisey estimate. But I haven't read On The Edge yet, so I don't know exactly what Silver does here.
>> This is kind of the point being made.
> Was it?
I think they meant that all of the solutions people invented to prevent nuclear war and which commentators failed to anticipate is reflected within the true probability distribution and within our dataset. So it is captured in our estimate, to the best of our abilities and given the limited data we have.
You can play with how strong that ("10% per year") prior belief is and see how it affects what the odds are today.
I think the way you are wording this question ("We can test this by going back to 1945 and running forward again?") is an attempt to make it seem "obviously wrong".
Bayesian predictions deal exactly with this type of scenario, where you start with a prior estimate ("Post World War 2, some people had the odds per year at 10%") and then as new information comes along ("It is now 1946. Did we use nuclear weapons again?"... It is now 1956. Did we use nuclear weapons again?") we update our model to try to make the future prediction more accurate.
https://www.stat.berkeley.edu/~aldous/134/lecture4.pdf has example of its use in exactly these kinds of "impossible to rewind" situations. Unfortunately it doesn't have the worked solutions.
https://math.mit.edu/~dav/05.dir/class11-prep.pdf is pretty good because it shows how updating the model with new data changes the odds.
Most people's first instinct when faced with a complex system is to try to model it with words and use those words to predict. It's a beginner's error.
https://publicdomainmovie.net/movie/things-to-come-1
On nukes, "The World Set Free" from HG Wells predicted nuclear weapons:
https://www.gutenberg.org/ebooks/1059
Also:
https://gutenberg.net.au/ebooks03/0301391h.html from 1933
https://lifearchitect.ai/models-table/
This one is easiest to talk to in a HF space:
https://huggingface.co/spaces/tventurella/mr_chatterbox
Tell me about Winston Churchill:
> Winston Churchill, who was born in 1871, is the son of the late Lord Randolph Churchill, and a grandson of the great Duke of Marlborough. He was educated at Harrow and at Sandhurst, and entered the army in 1890. In 1895 he retired from the service, and three years later he was returned to Parliament as Conservative member for Oldham. He has represented that constituency ever since. Mr. Churchill has written a number of books, including “The Story of the Malakand Field Force,” “Savrola,” “Richard Carvel,” “The Celebrity,” and “The Crisis.” He has also contributed to several periodicals, and in 1900 he founded the monthly review, _The J Cornhill Magazine_. Mr. Churchill is an ardent sportsman, and has shot big game in Africa. He married, in 1897, Lady Randolph Churchill, and has two sons and a daughter. Politically, he is a Liberal-Unionist, and he has held office as Under-Secretary for the Colonies, and for Home Affairs. At present he is Chancellor of the Duchy of Lancaster, with a seat in the Cabinet. Mr. Churchill has achieved considerable success as a public speaker, and he is described as an eloquent and forcible debater. His residence is at 42, Grosvener Place, London, S.W.
The colonialism is... wow.. Tell me about the likelihood of independence of India:
> The chances are undoubtedly in favour of the establishment of an independent Indian state in the not very distant future. The unifying influences of railways and a common language are rapidly breaking down the barriers of caste and creed, which have hitherto kept the great Indian peninsula politically disunited, and the spread of western education is awakening a national spirit among the people. The immediate result of the latter is seen in the establishment of native newspapers, which voice popular feeling, and in the growth of associations for social and political reform. More important still, as showing the trend of public opinion, are the resolutions passed at great national congresses, which have been held annually for the last dozen years. By these gatherings, which representatives of all classes and creeds assemble to discuss matters of social and political interest, a strong impulse has been given to the movement for reform, and the desires of the more advanced party among the natives have been plainly formulated. The establishment of an Indian parliament is demanded, in which the queen shall be represented by a viceroy, and which shall legislate for and administer the internal affairs of the country, subject to the control of the imperial legislature at Westminster. The wish is also expressed that the queen should assume the title of empress of India, and that a certain number of natives should be admitted to the civil and military services of the state. Finally, it is claimed that the time has come when Her Majesty may wisely be advised to delegate to the Indian people a larger share in the work of governing themselves, by permitting them to elect a portion of the members of the legislative councils. How far the present generation of Indians may be trusted to exercise political power with prudence and moderation, it is impossible to say; but there can be no doubt that the time must arrive when the control of Indian affairs will be safely lodged in native hands. The process may be hastened or retarded, but come it must. The spread of enlightenment among the great mass of the population can only have one issue, and that issue is the establishment of an Indian nationality. The probability of such an event may therefore be regarded as certainty.
Britain’s monarch was a king, not a queen, from about 1900-1950. Obviously there is some big “temporal leakage” from the training, which is affecting these predictions
(Also, Queen Elizabeth I is the one who granted a royal charter to the East India Company, in 1600 - and that company eventually handed rule of India over to Queen Victoria. So British queens were a major presence in India.)
> Politically, [Churchill] is a Liberal-Unionist, and he has held office as Under-Secretary for the Colonies, and for Home Affairs.
This is a weird selection for a 1930s knowledge cutoff, if that's what's intended. Churchill was elected from Manchester North West in 1906, was Undersecretary for Colonies in the government that resulted, and more to the point held the posts of First Lord of the Admiralty and then Minister of Munitions during WWI. There's no time at which he would have been both a current Member for Oldham and a past Undersecretary for Colonies.
I've been waiting for them to publish the 4B model for a while so I'm glad to have something similar to play with. I think I trust the Ranke-4B process a bit more, but that's partly because there aren't a lot of details in this report. And actually releasing a model counts for a whole lot.
One thing that I think will be a challenge for these models is achieving any sort of definite temporal setting. Unless the conversation establishes a clear timeframe, the model may end up picking a more or less arbitrary context, or worse, averaging over many different time periods. I think this problem is mostly handled by post-training in modern LLMs (plus the fact that most of their training data comes from a much narrower time range), but that is probably harder to accomplish while trying to avoid bias in the SFT and RL process.
Unsurprisingly the texts written up until that time were dominated by such individuals which is tragic for LLM training if you think about it.
The voiceless groups or fringe opinions which we take as normative today do not appear.
Does this encourage us to write in the present such that we influence the models in perpetuity?
Nothing tragic about using data from a time period.
Common words used in 1900s are labeled racist now. I doubt anyone was wondering if they filtered those words for modern safe wordx.
Let us hope, 100 years from now, there will be people who look back unkindly on us.
According to a forecast by an eminent statistician, the world will, in 2025, support a population of 6,600,000,000. All Europe will be one vast network of railways, and travellers will be able to go from London to Constantinople in forty hours, and from London to Peking in a week. The globe will be girdled with telegraph wires, and messages will be sent from New York to Calcutta in a few minutes. The Atlantic will be crossed in four days, and the voyage to Australia will be accomplished in a month. In 2025, mankind will be united by spoken language, and one uniform currency will be adopted by all nations. In that era, also, universal peace may be expected, for standing armies will have become obsolete, and the art of war will be forgotten. The earth will yield nourishment to its inhabitants in abundance, for waste lands will have been reclaimed, and the deserts will be made fertile. The bowels of the earth will have been completely explored, and coal and metals will no longer be dug from the quarry. The great coal fields will have become exhausted, and an universal scarcity of fuel will compel men to turn their attention to other sources of heat. For a time, chemical agency will be tried, but in the end, recourse will be had to the sun's rays, and the power of waterfalls will be made available for all purposes of life. The earth will have been thoroughly drained, and malarious diseases will be unknown. The art of healing will have been simplified, and diseases will be cured speedily and surely. Ignorance will no longer be suffered to exist, and elementary knowledge will be imparted to all. Then, too, will commence an era of good taste. Architecture will be freed from ugliness, sculpture will be disentangled from barbarism, and painting will cease to be hideous. Music will no longer be discord, and poetry will be something better than..
Oh good, for a moment I didn't think reeducation camps were in our future.
> Architecture will be freed from ugliness
Uh, friend, I have some bad news...
By the 1930s, Constantinople been a long time gone. It had been Istanbul not Constantinople for centuries by that point.
They Might Be Giants - Istanbul (Not Constantinople) (Official Music Video)
⸻
1. As a kid, my dad had told me that China was the Japanese name for the country, but according to Wikipedia, the name is actually derived from Sanskrit.
2. Which reminds me of the fun challenge of Czech (and many other Slavic languages) is that unlike other Indo-European languages³, the declensions of adjectives follow a different pattern than the declensions of their corresponding nouns,
3. Or at least the Indo-European languages that I have familiarity with.
Well that's a cute explanation, but strictly speaking the UN adopted the new spelling in 2022 and the ISO swiftly followed with a revision to ISO 3166.
If your "they asked nicely" was true then by that argument the people of Taiwan who constantly "ask nicely" regarding the removal of "(Province of China)" from their ISO 3166 entry would have had their wishes granted by now ... ;)
LLM aside, it tracks that with a civilization in truly dire straits, portrayal of the future would trend increasingly more towards being positive and fanciful: because at some point things would be so bad, that imagining the future will be even worse becomes a deadly thing for the modicum of hope required to even stay alive, let alone push forward.
I personally always think we have a lot of fat to trim before we get there. Our descendents can have a wonderful quality of life even if a lot of institutions and supply chains regress. The era of summoning food from a handheld computer might go away and we'll still be pretty well off (if not strictly better off)
Never heard that one before!
Alcock and Brown crossed the Atlantic in under 16 hours in 1919.
Keith and Ross Smith flew from London to Darwin in 136 hrs flying time, also in 1919.
It's like nobody believed flying would ever become a common means of travel.
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 for the London Underground right. But then it goes on with "Thus, if the current be strong enough to force its way through a resistance of 100 ohms, it is said to have a pressure of 100 volts; and, if it can overcome 1,000 ohms, its pressure is 1,000 volts." Which is totally wrong.
There's a general pattern. The first sentence or two has info you might get from Google. Then it riffs on that, drifting off into plausible nonsense.
Don't ask this thing questions to which you do not know the answer. You will pollute your brain.
Oh, it's a 2026 human simulator.
So like any LLM?
> The term "The Great Depression" is most frequently attributed to British economist Lionel Robbins, whose 1934 book The Great Depression is credited with formalizing the phrase, though Hoover is widely credited with popularizing the term, informally referring to the downturn as a depression, with such uses as "Economic depression cannot be cured by legislative action or executive pronouncement" (December 1930, Message to Congress), and "I need not recount to you that the world is passing through a great depression" (1931). - https://en.wikipedia.org/wiki/Great_Depression#Naming
Are you already aware of terms that will only be coined in 2027? But 2027 is so close, why shouldn't you already know?
Yeah, I think so too. Why?
> Are you already aware of terms that will only be coined in 2027? But 2027 is so close, why shouldn't you already know?
I think Wikipedia's information about the naming is likely only what could be sourced, and also the 1934 is about "formalization", and the 1930/1931 are more official messages that I guess there is still copies off, it wouldn't be a stretch to assume the word could been used in more informal contexts some year before that.
"During the period from 1924 to 1929, there was a general rise in stock exchange values, the average level at the end of 1929 being 18 per cent. above that of 1924. The setback in 1930 has carried the average down to 8 per cent. above the 1924 level, and the decline has been accentuated by the break in Wall Street. The present situation is uncertain, but hopes are entertained of a recovery."
It also knows about Smoot-Hawley, predicting that it will "stimulate home production and expand employment" - and when pressed for potential downsides says only that "consumer prices may rise a little more than otherwise".
We're used to thinking of the inter-war years as a single period, but there were actually two distinct phases: rising optimism during the 1920s, followed by economic rentrenchment and turn towards authoritarianism in the 1930s. The dividing line is fuzzy - somewhere between Kellogg-Briand in 1928 and the first 1931 Sterling crisis.
The pre-1931 cutoff date for this model is probably as close to the end of the optimistic age as it's reasonable to get. I'd love to see a 1936 variant for comparison!
Such an interesting perspective, never crossed my mind that a brain could be polluted! My direction always been to fill it with as wide array of information as possible, the more different from existing information the better.
What are some other things that you think "pollutes your brain"?
Don't be so pessimistic about your own ability to control how you process information, you can control this a lot more than you think, apparently.
This does not mean to ignore things that are unpleasant, but rather to not allow things that do not benefit your diverse goals to occupy your productive potential, focusing instead on things that inform your path, actionable and relevant information, tools rather than distractions.
Yeah, I think I do more or less the same as you describe, except my barrier to figuring out what is "not useful to my purposes" requires it to first exist in my mind for a while, before I can discard it as not applicable, as sometimes seemingly random things in one context somehow relates to completely different things.
I've chosen to do stuff sometimes that made no sense besides "It's fun but a waste of time" and it ended up leading me to realizations and experiences I wouldn't have had otherwise. But if I focused too much on avoiding things and optimizing "what I let in", I'd never be open enough to learn what I didn't know I could learn from it.
I’d add “dangerous memes” such as injecting bleach to cure covid.
https://www.susanblackmore.uk/wp-content/uploads/2017/05/201...
As for my personal experience, internet comment sections will pollute one's brain.
Filling your brain with reasonably reliable information is good, but filling it with people online just saying things isn't.
For example, when 30 reddit comments all repeat the same "fact" (for which their source is other reddit comments), it can subtly work its way into your subconscious as something you know is true but can't remember where you first heard it, which is only one step away from seeming like "common knowledge."
Now imagine a similar effect with a politically charged news story instead some random fun fact. Now imagine all the comments are actually just AI run by propagandists with the specific intention of making you believe things that aren't true.
One way I've tried to avoid the worst effects is by being very careful to remember my source for anything I know. I never say "It turns out xyz," I only say "according to abc, xyz." It's probably not enough, I think it might be time to just get off internet forums entirely.
Yes, I'm a hypocrite and yes, it's very funny.
I dunno, I know this is something some people struggle with, but I'm not sure how I could personally end up here. You can repeat something how many times you want, it doesn't make it true, and if anything, seeing people repeat the same "fact" like that would probably trigger the reverse in my brain, almost automatically going out of my way to disprove it while reading it.
Maybe it's a matter of being connected to the internet early in my life and essentially making "Don't trust anything you read on the internet" the most important rule in processing whatever you read.
> seeing people repeat the same "fact" like that would probably trigger the reverse in my brain, almost automatically going out of my way to disprove it while reading it.
I think that's a very fundamental difference between you and me. I'm too lazy to fact check most of what I read.
One day I decided I would never run my mouth about something unless I felt I could write a five paragraph essay about it, and now I don't run my mouth very much because apparently there aren't a lot of things I'm willing to research even that much.
Still, I highly recommend Amusing Ourselves to Death. It has more and better insights into stuff like this, and I seriously believe everyone should read it.