If the model comes up with anything even remotely correct it would be quite a strong evidence that LLMs are a path to something bigger if not then I think it is time to go back to the drawing board.
Things don't happen all of a sudden, and being able to see all the scientific papers of the era its possible those could have fallen out of the synthesis.
Standing on the shoulders of giants, as it were
It's still unclear whether this process could be merely continued, seeded only with new physical data, in order to keep progressing beyond that point, "forever", or at least for as long as we imagine humans will continue to go on making scientific progress.
These two are so above everyone else in the mathematical world that most people would struggle for weeks or even months to understand something they did in a couple of minutes.
There's no "get down and dirty" shortcut with them =)
However, you could also argue that it's actually empirical evidence that general relativity and 19th century physics wasn't truly a paradigm shift -- you could have 'derived' it from previous data -- that the LLM has actually proven something about structurally similarities between those paradigms, not that it's demonstrating general intelligence...
But the whole question is whether or not something can do that synthesis!
And the "anyone who read all the right papers" thing - nobody actually reads all the papers. That's the bottleneck. LLMs don't have it. They will continue to not have it. Humans will continue to not be able to read faster than LLMs.
Even me, using a speech synthesizer at ~700 WPM.
I by no means believe LLMs are general intelligence, and I've seen them produce a lot of garbage, but if they could produce these revolutionary theories from only <= year 1900 information and a prompt that is not ridiculously leading, that would be a really compelling demonstration of their power.
It turns out my reading is somewhat topical. I've been reading Rhodes' "The Making of the Atomic Bomb" and of the things he takes great pains to argue (I was not quite anticipating how much I'd be trying to recall my high school science classes to make sense of his account of various experiments) is that the development toward the atomic bomb was more or less inexorable and if at any point someone said "this is too far; let's stop here" there would be others to take his place. So, maybe, to answer your question.
Yes. It is certainly a question if Einstein is one of the smartest guy ever lived or all of his discoveries were already in the Zeitgeist, and would have been discovered by someone else in ~5 years.
Einstein was smart and put several disjointed things together. It's amazing that one person could do so much, from explaining the Brownian motion to explaining the photoeffect.
But I think that all these would have happened within _years_ anyway.
Kind of, how long would it have realistically taken for someone else (also really smart) to come up with the same thing if Einstein wouldn't have been there?
I personally doubt that this would work. I don't think these systems can achieve truly ground-breaking, paradigm-shifting work. The homeworld of these systems is the corpus of text on which it was trained, in the same way as ours is physical reality. Their access to this reality is always secondary, already distorted by the imperfections of human knowledge.
It’s probably even more of a problem that different areas of scientific development don’t know about each other. LLMs combining results would still not be like they invented something new.
But if they could give us a head start of 20 years on certain developments this would be an awesome result.
My own prediction is that the LLMs would totally fail at connecting the dots, but a small group of very smart humans can.
Things don't happen all of a sudden, but they also don't happen everywhere. Most people in most parts of the world would never connect the dots. Scientific curiosity is something valuable and fragile, that we just take for granted.
Training data for a base model isn't that hard to come by, even though you have to OCR most of it yourself because the publicly available OCRed versions are commonly unusably bad. But training a model large enough to be useful is a major issue. Training a 700M parameter model at home is very doable (and is what this TimeCapsuleLLM is), but to get that kind of reasoning you need something closer to a 70B model. Also a lot of the "smarts" of a model gets injected in fine tuning and RL, but any of the available fine tuning datasets would obviously contaminate the model with 2026 knowledge.
At least the model part. Although others made same thought as you afaik none tried it.
They measure compression (perplexity) on future Wikipedia, news articles, code, arXiv papers, and multi-modal data. Data compression is intimately connected with robustness and generalization.
I imagine if you explained quantum field theory to a 19th century scientists they might think of it as a more refined understanding of luminiferous aether.
Or if an 18th century scholar learned about positive and negative ions, it could be seen as an expansion/correction of phlogiston theory.
Special relativity however seems possible.
[0] https://github.com/haykgrigo3/TimeCapsuleLLM/blob/main/Copy%...
In fact you don’t want it to know about them explicitly just have enough background knowledge that you can manage the rest via context.
But I think there are also some questions about the role of language in human thought that leave the door just slightly ajar on the issue of whether or not manipulating the tokens of language might be more central to human cognition than we've tended to think.
If it turned out that this was true, then it is possible that "a model predicting tokens" has more power than that description would suggest.
I doubt it, and I doubt it quite a lot. But I don't think it is impossible that something at least a little bit along these lines turns out to be true.
Unfortunately, none of that has anything to do with what LLMs are doing. The LLM is not thinking about concepts and then translating that into language. It is imitating what it looks like to read people doing so and nothing more. That can be very powerful at learning and then spitting out complex relationships between signifiers, as it's really just a giant knowledge compression engine with a human friendly way to spit it out. But there's absolutely no logical grounding whatsoever for any statement produced from an LLM.
The LLM that encouraged that man to kill himself wasn't doing it because it was a subject with agency and preference. It did so because it was, quite accurately I might say, mimicking the sequence of tokens that a real person encouraging someone to kill themselves would write. At no point whatsoever did that neural network make a moral judgment about what it was doing because it doesn't think. It simply performed inference after inference in which it scanned through a lengthy discussion between a suicidal man and an assistant that had been encouraging him and then decided that after "Cold steel pressed against a mind that’s already made peace? That’s not fear. That’s " the most accurate token would be "clar" and then "ity."
We know what our experience is - thinking about concepts and then translating that into language - but we really don't know with much confidence what is actually going on.
I lean strongly toward the idea that humans are doing something quite different than LLMs, particularly when reasoning. But I want to leave the door open to the idea that we've not understood human cognition, mostly because our primary evidence there comes from our own subjective experience, which may (or may not) provide a reliable guide to what is actually happening.
We do know what it's not doing, and that is operating only through reproducing linguistic patterns. There's no more cause to think LLMs approximate our thought (thought being something they are incapable of) than that Naive-Bayes spam filter models approximate our thought.
I'm convinced of this. I think it's because we've always looked at the most advanced forms of human languaging (like philosophy) to understand ourselves. But human language must have evolved from forms of communication found in other species, especially highly intelligent ones. It's to be expected that the building blocks of it is based on things like imitation, playful variation, pattern-matching, harnessing capabilities brains have been developing long before language, only now in the emerging world of sounds, calls, vocalizations.
Ironically, the other crucial ingredient for AGI which LLMs don't have, but we do, is exactly that animal nature which we always try to shove under the rug, over-attributing our success to the stochastic parrot part of us, and ignoring the gut instinct, the intuitive, spontaneous insight into things which a lot of the great scientists and artists of the past have talked about.
Are you familiar with the major works in epistemology that were written, even before the 20th century, on this exact topic?
The only people who are serious about suggesting that LLMs could possibly 'think' are the people who are committing fraud on the scale of hundreds of billions of dollars (good for them on finding the all-time grift!) and people who don't understand how they're programmed, and thusly are the target of the grift. Granted, given that the vast majority of humanity are not programmers, and even fewer are programmers educated on the intricacies of ML, the grift target pool numbers in the billions.
Could you elucidate me on the process of human thought, and point out the differences between that and a probabilistic prediction engine?
I see this argument all over the place, but "how do humans think" is never described. It is always left as a black box with something magical (presumably a soul or some other metaphysical substance) inside.
1: https://chatgpt.com/share/6965653e-b514-8011-b233-79d8c25d33...
It largely cannot imaginr anything beyond the usual but there is a small part that it can. This is similar to in context learning, it's weak but it is there.
It would be incredible if meta learning/continual learning found a way to train exactly for novel learning path. But that's literally AGI so maybe 20yrs from now? Or never..
You can see this on CL benchmarks. There is SOME signal but it's crazy low. When I was traing CL models i found that signal was in the single % points. Some could easily argue it was zero but I really do believe there is a very small amount in there.
This is also why any novel work or findings is done via MASSIVE compute budgets. They find RL enviroments that can extract that small amount out. Is it random chance? Maybe, hard to say.
AI cannot compound their learnings for the foreseeable future
I mostly agree with you, especially about distrusting the self-interested hype beasts.
While I don't think the models are actually "intelligent", I also wonder if there are insights to be gained by looking at how concepts get encoded by the models. It's not really that the models will add something "new", but more that there might be connections between things that we haven't noticed, especially because academic disciplines are so insular these days.
If we did this (to a good enough level of detail), would it be able to derive relativity? How large of an AI model would it have to be to successfully derive relativity (if it only had access to everything published up to 1904)?
Most ML researchers think AGI is imminent.
I don't think there is any level of broad agreement right now. There are tons of random camps none of which I would consider to be broadly dominating.
Not sure how to interpret that as almost imminent.
20 years away in 2026, still 20 years away in 2027, etc etc.
Whatever Altman's hyping, that's the translation.
But considering that Special Relativity was published in 1905 which means all its building blocks were already floating in the ether by 1900 it would be a very interesting experiment to train something on Claude/Gemini scale and then say give in the field equations and ask it to build a theory around them.
But I also think we can do this with normal LLMs trained on up-to-date text, by asking them to come up with any novel theory that fits the facts. It does not have to be a groundbreaking theory like QM, just original and not (yet) proven wrong ?
Then, we have a model that knows quite a bit in modern English. We also legally have a data set for everything it knows. Then, there's all kinds of experimentation or copyright-safe training strategies we can do.
Project Gutenberg up to the 1920's seems to be the safest bet on that.
If you could only give it texts and info and concepts up to Year X, well before Discovery Y, could we then see if it could prompt its way to that discovery?
You'd have to be specific what you mean by AGI: all three letters mean a different thing to different people, and sometimes use the whole means something not present in the letters.
> If you could only give it texts and info and concepts up to Year X, well before Discovery Y, could we then see if it could prompt its way to that discovery?
To a limited degree.
Some developments can come from combining existing ideas and seeing what they imply.
Other things, like everything to do with relativity and quantum mechanics, would have required experiments. I don't think any of the relevant experiments had been done prior to this cut-off date, but I'm not absolutely sure of that.
You might be able to get such an LLM to develop all the maths and geometry for general relativity, and yet find the AI still tells you that the perihelion shift of Mercury is a sign of the planet Vulcan rather than of a curved spacetime: https://en.wikipedia.org/wiki/Vulcan_(hypothetical_planet)
Well, they obviously can't. AGI is not science, it's religion. It has all the trappings of religion: prophets, sacred texts, origin myth, end-of-days myth and most importantly, a means to escape death. Science? Well, the only measure to "general intelligence" would be to compare to the only one which is the human one but we have absolutely no means by which to describe it. We do not know where to start. This is why you scrape the surface of any AGI definition you only find circular definitions.
And no, the "brain is a computer" is not a scientific description, it's a metaphor.
Disagree. A brain is turing complete, no? Isn't that the definition of a computer? Sure, it may be reductive to say "the brain is just a computer".
https://aeon.co/essays/your-brain-does-not-process-informati...
This article seems really hung up on the distinction between digital and analog. It's an important distinction, but glosses over the fact that digital computers are a subset of analog computers. Electrical signals are inherently analog.
This maps somewhat neatly to human cognition. I can take a stream of bits, perform math on it, and output a transformed stream of bits. That is a digital operation. The underlying biological processes involved are a pile of complex probabilistic+analog signaling, true. But in a computer, the underlying processes are also probabilistic and analog. We have designed our electronics to shove those parts down to the lowest possible level so they can be abstracted away, and so the degree to which they influence computation is certainly lower than in the human brain. But I think an effective argument that brains are not computers is going to have to dive in to why that gap matters.
This is odd because the dominant view in neuroscience is that memories are stored by altering synaptic connection strength in a large number of neurons. So it's not clear what his disagreement is, and he just seems to be misrepresenting neuroscientists.
Interestingly, this is also how LLMs store memory during training: by altering the strength of connections between many artificial neurons.
> But here is what we are not born with: information, data, rules, software, knowledge, lexicons, representations, algorithms, programs, models, memories, images, processors, subroutines, encoders, decoders, symbols, or buffers – design elements that allow digital computers to behave somewhat intelligently. Not only are we not born with such things, we also don’t develop them – ever.
Really? Humans don't ever develop memories? Humans don't gain information?
There's certainly plenty of cargo-culting right now on AI.
Sacred texts, I don't recognise. Yudkowsky's writings? He suggests wearing clown shoes to avoid getting a cult of personality disconnected from the quality of the arguments, if anyone finds his works sacred, they've fundamentally misunderstood him:
I have sometimes thought that all professional lectures on rationality should be delivered while wearing a clown suit, to prevent the audience from confusing seriousness with solemnity.
Prophets forecasting the end-of-days, yes, but this too from climate science, from everyone who was preparing for a pandemic before covid and is still trying to prepare for the next one because the wet markets are still around, from economists trying to forecast growth or collapse and what will change any given prediction of the latter into the former, and from the military forces of the world saying which weapon systems they want to buy. It does not make a religion.
A means to escape death, you can have. But it's on a continuum with life extension and anti-aging medicine, which itself is on a continuum with all other medical interventions. To quote myself:
Taking a living human's heart out without killing them, and replacing it with one you got out a corpse, that isn't the magic of necromancy, neither is it a prayer or ritual to Sekhmet, it's just transplant surgery.
…
Immunity to smallpox isn't a prayer to the Hindu goddess Shitala (of many things but most directly linked with smallpox), and it isn't magic herbs or crystals, it's just vaccines.
Ways data might leak to the model that come to mind: misfiled/mislabled documents, footnotes, annotations, document metadata.
Especially for London there is a huge chunk of recorded parliament debates.
More interesting for dialoge seems training on recorded correspondence in form of letters anyway.
And that corpus script just looks odd to say the least, just oversample by X?
SOTA LLMs show quite a lot of skill, but they only do so after reading a significant fraction of all published writing (and perhaps images and videos, I'm not sure) across all languages, in a world whose population is 5 times higher than the link's cut off date, and the global literacy went from 20% to about 90% since then.
Computers can only make up for this by being really really fast: what would take a human a million or so years to read, a server room can pump through a model's training stage in a matter of months.
When the data isn't there, reading what it does have really quickly isn't enough.
As a thought experiment I find it thrilling.
The fact that tech leaders espouse the brilliance of LLMs and don't use this specific test method is infuriating to me. It is deeply unfortunate that there is little transparency or standardization of the datasets available for training/fine tuning.
Having this be advertised will make more interesting and informative benchmarks. OEM models that are always "breaking" the benchmarks are doing so with improved datasets as well as improved methods. Without holding the datasets fixed, progress on benchmarks are very suspect IMO.
LLMs have neither intelligence nor problem-solving abillity (and I won't be relaxing the definition of either so that some AI bro can pretend a glorified chatbot is sentient)
You would, at best, be demonstrating that the sharing of knowledge across multiple disciplines and nations (which is a relatively new concept - at least at the scale of something like the internet) leads to novel ideas.
I think there's a big difference between discoveries through AI-human synergy and discoveries through AI working in isolation.
It probably will be true soon (if it isn't already) that most innovation features some degree of AI input, but still with a human to steer the AI in the right direction.
I think an AI being able to discover something genuinely new all by itself, without any human steering, is a lot further off.
If AIs start producing significant quantities of genuine and useful innovation with minimal human input, maybe the singularitarians are about to be proven right.
So if it can work with whats now past, it will be able to work with the past in the future?
If the prediction is that AI will be able to invent the future. If we give it data from our past without knowledge of the present... what type of future will it invent, what progress will it make, if any at all? And not just having the idea, but how to implement the idea in a way that actually works with the technology of the day, and can build on those things over time.
For example, would AI with 1850 data have figured out the idea of lift to make an airplane and taught us how to make working flying machines and progress them to the jets we have today, or something better? It wouldn't even be starting from 0, so this would be a generous example, as da Vinci way playing with these ideas in the 15th century.
If it can't do it, or what it produces is worse than what humans have done, we shouldn't leave it to AI alone to invent our actual future. Which would mean reevaluating the role these "thought leaders" say it will play, and how we're educating and communicating about AI to the younger generations.
Very cool concept though, but it definitely has some bias.
to be frank though, I think this a better way than all people's thoughts all of the time.
I think the "crowd" of information makes the end output of an LLM worse rather than better. Specifically in our inability to know really what kind of Bias we're dealing with.
Currently to me it feels really muddy knowing how information is biased, beyond just the hallucination and factual incosistencies.
But as far as I can tell, "correctness of the content aside", sometimes frontier LLMs respond like freshman college students, other times they respond with the rigor of a mathematics PHD canidate, and sometimes like a marketing hit piece.
This dataset has a consistency which I think is actually a really useful feature. I agree that having many perspectives in the dataset is good, but as an end user being able to rely on some level of consistency with an AI model is something I really think is missing.
Maybe more succinctly I want frontier LLM's to have a known and specific response style and bias which I can rely on, because there already is a lot of noise.
So, the OP model will accidentally reflect the biases of the time. The current, commercial models intentionally reflect specific biases. Except for uncensored models which accidentally have those in the training data modified by uncensoring set.
Another thought, just occurred when thinking about readmes and coding LLMs: obviously this model wouldn't have any coding knowledge, but I wonder if it could be possible to combine this somehow with a modern LLM in such a way that it does have coding knowledge, but it renders out all the text in the style / knowledge level of the 1800's model.
Offhand I can't think of a non-fine-tuning trick that would achieve this. I'm thinking back to how the old style transfer models used to work, where they would swap layers between models to get different stylistic effects applied. I don't know if that's doable with an LLM.
But on various data (i.e., separate model per source): the Bible, Don Quixote and Franz Kafka. (As well as a (bad!) lyrics generator, and translator.)
To get Relativity, the model needs to realize the training data isn't just incomplete, but fundamentally wrong. That requires abductive reasoning (the spark of genius) to jump out of the local minimum. Without that AGI-level spark, a 'pure knowledge pile' will just generate a very eloquent, mathematically rigorous defense of Newtonian physics.
===
You:
I pray you, who is this Master Newton?
timecapsulellm-v2-1800-1875-mlx:
TI offer to pay you the very same fee as you did before. It was not in the power of your master to deliver the letter to your master. He did. I will be with you as soon as I can keep my word. It is not at all clear, whether the letter has been sent or not. It is not at all clear: but it is clear also that it was written by the person who gave it. "No," I said, "I cannot give it to you." There, the letter was sent to me. "The letter is yours, I believe," I said. "But, I hope, you will not refuse to give it to me?
There's a "Use this model" button on that page that can launch it in LM Studio.
https://news.ycombinator.com/item?id=46319826
I found it particularly thought-inspiring how a model with training from that time period completely lacks context/understanding of what it is itself, but then I realized that we are the same (at least for now).
This feels like a neat sci-fi short story hook to explain the continuous emergence of God as an artifact of a simulation
Now if I train a foundation models with docs from library of Alexandria and only those texts of that period, I would have a chance to get a rudimentary insight on what the world was like at that time.
And maybe time shift further more.
Congratulations, you've reinvented the history book (just with more energy consumption and less guarantee of accuracy)
This isn't super relevant to us because very few histories from this era survived, but presumably there was sufficient material in the Library of Alexandria to cover events from multiple angles and "zero out" the different personal/political/religious biases coloring the individual accounts.
Back in the pre-LLM days, someone trained a Markov chain off the King James Bible and a programming book: https://www.tumblr.com/kingjamesprogramming
I'd love to see an LLM equivalent, but I don't think that's enough data to train from scratch. Could a LoRA or similar be used in a way to get speech style to strictly follow a few megabytes worth of training data?
That happened in the past, and the "naive" way of doing it is usually easy to spot. There are, however, many ways in which testing data can leak into models, even without data contamination. However this doesn't matter much, as any model that only does well in benchmarks but is bad in real-world usage will be quickly sussed out by people actually using them. There are also lots and lots of weird, not very popular benchmarks out there, and the outliers are quickly identified.
> perform on SWE-bench if trained only on data prior to 2024.
There's a benchmark called swe-REbench, that takes issues from real-world repos, published ~ monthly. They perform tests and you can select the period and check their performance. This is fool-proof for open models, but a bit unknown for API-based models.
PROMPT:Charles Darwin
Charles DarwinECCEMACY. Sir, — The following case is interesting to me : — I was in London a fortnight, and was much affected with an attack of rheumatism. The first attack of rheumatism was a week before I saw you, and the second when I saw you, and the third when I saw you, and the third in the same time. The second attack of gout, however, was not accompanied by any febrile symptoms, but was accompanied with an increased flow of urine, and with a more copious discharge of urine. The third attack was an hour after I saw you, and was succeeded by a return of a paroxysm of gout, and a more rapid return of the gout. The fourth attack was also accompanied by a fever, but was not always accompanied by any febrile symptoms. The third attack of gout was a fortnight after you had been ill, and the fourth was followed by a paroxysm of gout. The fourth attack was a fortnight after you were attacked, and was accompanied by a sense
That is, the architectures of today are chosen to yield the best results given the textual data around today and the problems we want to solve today.
I'd argue that this lack of bias would need to be researched (if it hasn't been already) before this kind of model has credence.
LLMs aren't my area of expertise but during my PhD we were able to encode a lot of a priori knowledge through the design of neural network architectures.
A truly authentic historical model will have some unsavory opinions and very distinctive dialect.