[HN Gopher] Transformers know more than they can tell: Learning ...
       ___________________________________________________________________
        
       Transformers know more than they can tell: Learning the Collatz
       sequence
        
       Author : Xcelerate
       Score  : 100 points
       Date   : 2025-12-03 17:50 UTC (6 days ago)
        
 (HTM) web link (www.arxiv.org)
 (TXT) w3m dump (www.arxiv.org)
        
       | niek_pas wrote:
       | Can someone ELI5 this for a non-mathematician?
        
         | poszlem wrote:
         | A transformer can. Here gemini:
         | 
         | The Experiment: Researchers trained AI models (Transformers) to
         | solve a complex arithmetic problem called the "long Collatz
         | step".
         | 
         | The "Language" Matters: The AI's ability to solve the problem
         | depended entirely on how the numbers were written. Models using
         | bases divisible by 8 (like 16 or 24) achieved nearly 100%
         | accuracy, while those using odd bases struggled significantly.
         | 
         | Pattern Matching, Not Math: The AI did not learn the actual
         | arithmetic rules. Instead, it learned to recognize specific
         | patterns in the binary endings of numbers (zeros and ones) to
         | predict the answer.
         | 
         | Principled Errors: When the AI failed, it didn't hallucinate
         | random answers. It usually performed the correct calculation
         | but misjudged the length of the sequence, defaulting to the
         | longest pattern it had already memorized.
         | 
         | Conclusion: These models solve complex math by acting as
         | pattern recognizers rather than calculators. They struggle with
         | the "control structure" (loops) of algorithms unless the input
         | format reveals the answer through shortcuts.
        
           | embedding-shape wrote:
           | Do you think maybe OP would have asked a language model for
           | the answer if they felt like they wanted a language model to
           | give an answer? Or in your mind parent doesn't know about
           | LLMs, and this is your way of introducing them to this
           | completely new concept?
        
             | NitpickLawyer wrote:
             | Funny that the "human" answer above took 2 people to be
             | "complete" (i.e. an initial answer, followed by a
             | correction and expansion of concepts), while the LLM one
             | had mostly the same explanation, but complete and in one
             | answer.
        
               | embedding-shape wrote:
               | Maybe most of us here don't seek just whatever answer to
               | whatever question, but the human connection part of it is
               | important too, that we're speaking with real humans that
               | have real experience with real situations.
               | 
               | Otherwise I'd just be sitting chatting with ChatGPT all
               | day instead of wast...spending all day on HN.
        
               | pixl97 wrote:
               | If life is a jobs program, why don't we dig ditches with
               | spoons?
        
               | NitpickLawyer wrote:
               | Oh, I agree. What I found funny is the gut reaction of
               | many other readers that downvoted the message (it's
               | greyed out for me at time of writing this comment).
               | Especially given that the user clearly mentioned that it
               | was LLM generated, while also being cheeky with the
               | "transformer" pun, on a ... transformer topic.
        
         | esafak wrote:
         | The model partially solves the problem but fails to learn the
         | correct loop length:
         | 
         | > An investigation of model errors (Section 5) reveals that,
         | whereas large language models commonly "hallucinate" random
         | solutions, our models fail in principled ways. In almost all
         | cases, the models perform the correct calculations for the long
         | Collatz step, but use the wrong loop lengths, by setting them
         | to the longest loop lengths they have learned so far.
         | 
         | The article is saying the model struggles to learn a particular
         | integer function.
         | https://en.wikipedia.org/wiki/Collatz_conjecture
        
           | spuz wrote:
           | That's a bit of an uncharitable summary. In bases 8, 12, 16,
           | 24 and 32 their model achieved 99.7% accuracy. They would
           | never expect it to achieve 100% accuracy. It would be like if
           | you trained a model to predict whether or not a given number
           | is prime. A model that was 100% accurate would defy
           | mathematical knowledge but a model that was 99.7% would
           | certainly be impressive.
           | 
           | In this case, they prove that the model works by categorising
           | inputs into a number of binary classes which just happen to
           | be very good predictors for this otherwise random seeming
           | sequence. I don't know whether or not some of these binary
           | classes are new to mathematics but either way, their
           | technique does show that transformer models can be helpful in
           | uncovering mathematical patterns even in functions that are
           | not continuous.
        
             | jacquesm wrote:
             | A pocket calculator that would give the right numbers 99.7%
             | of the time would be fairly useless. The lack of
             | determinism is a problem and there is nothing
             | 'uncharitable' about that interpretation. It is definitely
             | impressive, but it is fundamentally broken, because when
             | you start making chains of things that are 99.7% correct
             | you end up with garbage after very few iterations. That's
             | precisely why digital computers won out over analog ones,
             | the fact that they are deterministic.
        
               | fkarg wrote:
               | yeah it's only correct in 99.7% of all cases, but what if
               | it's also 10'000 times faster? There's a bunch of
               | scenarios where that combination provides a lot of value
        
               | jacquesm wrote:
               | Correctness in software is the first rung of the ladder,
               | optimizing before you have correct output is in almost
               | all cases a complete waste of time. Yes, there are a some
               | scenarios where having a ballpark figure quickly can be
               | useful _if_ you can produce the actual result as well and
               | if you are not going to output complete nonsense the
               | other times but something that approaches the final
               | value. There are a lot of algorithms that do this (for
               | instance: Newton 's method for finding square roots).
               | 
               | 99.7% of the time good and 0.3% of the time noise is not
               | very useful, especially if there is no confidence
               | indicating that the bad answers are probably incorrect.
        
               | lkey wrote:
               | Ridiculous counterfactual. The LLM started failing 100%
               | of the time 60! _orders of magnitude_ sooner than the
               | point at which we have checked literally every number.
               | 
               | This is not even to mention the fact that asking a GPU to
               | _think about_ the problem will _always_ be less efficient
               | than just asking that GPU to directly compute the result
               | for closed algorithms like this.
        
               | pixl97 wrote:
               | Why do people keep using LLMs as algorithms?
               | 
               | LLMs are not calculators. If you want a calculator use a
               | calculator. Hell, have your LLM use a calculator.
               | 
               | >That's precisely why digital computers won out over
               | analog ones, the fact that they are deterministic.
               | 
               | I mean, no not really, digital computers are _far_ easier
               | to build and far more multi-purpose (and technically the
               | underlying signals are analog).
               | 
               | Again, if you have a deterministic solution that is 100%
               | correct all the time, use it, it will be cheaper than an
               | LLM. People use LLMs because there are problems that are
               | either not deterministic or the deterministic solution
               | uses more energy than will ever be available in the local
               | part of our universe. Furthermore a lot of AI (not even
               | LLMs) use random noise at particular steps as a means to
               | escape local maxima.
        
               | jacquesm wrote:
               | > Why do people keep using LLMs as algorithms?
               | 
               | I think they keep coming back to this because a good
               | command of math underlies a vast domain of applications
               | and without a way to do this as part of the reasoning
               | process the reasoning process itself becomes susceptible
               | to corruption.
               | 
               | > LLMs are not calculators. If you want a calculator use
               | a calculator. Hell, have your LLM use a calculator.
               | 
               | If only it were that simple.
               | 
               | > I mean, no not really, digital computers are far easier
               | to build and far more multi-purpose (and technically the
               | underlying signals are analog).
               | 
               | Try building a practical analog computer for a non-
               | trivial problem.
               | 
               | > Again, if you have a deterministic solution that is
               | 100% correct all the time, use it, it will be cheaper
               | than an LLM. People use LLMs because there are problems
               | that are either not deterministic or the deterministic
               | solution uses more energy than will ever be available in
               | the local part of our universe. Furthermore a lot of AI
               | (not even LLMs) use random noise at particular steps as a
               | means to escape local maxima.
               | 
               | No, people use LLMs for _anything_ and one of the weak
               | points in there is that as soon as it requires slightly
               | more complex computation there is a fair chance that the
               | output is nonsense. I 've seen this myself in a bunch of
               | non-trivial trials regarding aerodynamic calculations,
               | specifically rotation of airfoils relative to the
               | direction of travel. It tends to go completely off the
               | rails if the problem is non-trivial and the user does not
               | break it down into roughly the same steps as you would if
               | you were to work out the problem by hand (and even then
               | it may subtly mess up).
        
               | spuz wrote:
               | It's uncharitable because the comment purports to
               | summarise the entire paper while simply cherry picking
               | the worst result. It would be like if asked how did I do
               | on my test and you said well you got question 1 wrong and
               | then didn't elaborate.
               | 
               | Now I get your point that a function that is 99.7%
               | accurate will eventually always be incorrect but that's
               | not what the comment said.
        
               | esafak wrote:
               | I just tried to get to the heart of the claim based on a
               | skim. Please feel free to refine my summary.
        
               | beambot wrote:
               | Most primality tests aren't 100% accurate either (eg
               | Miller Rabin), they just are "reasonably accurate" while
               | being very fast to compute. You can use them in
               | conjunction to improve your confidence in the result.
        
               | jacquesm wrote:
               | Yes, and we _know_ they are inaccurate and we know that
               | if you find a prime that way you can only use it to
               | reject, not confirm so if you think that something is
               | prime you need to check it.
               | 
               | But now imagine that instead of it being a valid reject
               | 0.3% of the time it would also reject valid primes. Now
               | it would be instantly useless because it fails the test
               | for determinism.
        
               | brokensegue wrote:
               | I don't know people are saying it's useful. Just
               | interesting
        
               | briandw wrote:
               | Category error. You want 100% accuracy for an impossible
               | problem. This is a famously unsolved conjecture. The only
               | way to get the answer is to fully calculate it. The task
               | was to make a guess and see how well it could do. 99.7 is
               | surprisingly good. If the task was to calculate, the llm
               | could write a python program, just like I would have if
               | asked to calculate the answer.
        
               | jacquesm wrote:
               | There is a massive difference between an 'unsolved
               | problem' and a problem solved 'the wrong way'. Yes, 99.7%
               | is surprisingly good. But it did not detect the errors in
               | its own output. And it should have.
               | 
               | Besides, we're all stuck on the 99.7% as if that's the
               | across the board output, but that's a cherry picked
               | result:
               | 
               | "The _best_ models (bases 24, 16 and 32) achieve a near-
               | perfect accuracy of 99.7%, while odd-base models struggle
               | to get past 80%. "
               | 
               | I do think it is a very interesting thing to do with a
               | model and it _is_ impressive that it works at all.
        
               | godelski wrote:
               | Category error.
               | 
               | The problem here is deterministic. * _It must be for
               | accuracy to even be measured*_.
               | 
               | The model isn't trying to solve the Collatz conjecture,
               | it is learning a pretty basic algorithm and then doing
               | this a number of times. The instructions it needs to
               | learn is                 if x % 2:           x /= 2
               | else:           x = x*3 + 1
               | 
               | It _also_ needs to learn to put that in a loop and for
               | that to be a variable, but the algorithm is static.
               | 
               | On the other hand, the Collatz conjecture states that for
               | C(x) (the above algorithm) has a fixed point of 1 for all
               | x (where x \in Z+). Meaning that eventually any input
               | will collapse to the loop 1 -> 4 -> 2 -> 1 (or just
               | terminate at 1). You can probably see we know this is
               | true for at least an infinite set of integers...
               | 
               | Edit: I should note that there is a slight modification
               | to this, though model could get away with learning just
               | this. Their variation limits to odd numbers and not all
               | of them. For example 9 can't be represented by (2^k)m - 1
               | (but 7 and 15 can). But you can see that there's still a
               | simple algorithm and that the crux is determining the
               | number of iterations. Regardless, this is still
               | deterministic. They didn't use any integers >2^71, which
               | we absolutely know the sequences for and we absolutely
               | know all terminate at 1.
               | 
               | To solve the Collatz Conjecture (and probably win a
               | Fields Metal) you _must_ do one of 2 things.
               | 1) Provide a counter-example        2) Show that this
               | happens for all n, which is an infinite set of numbers,
               | so this strictly cannot be done by demonstration.
        
               | famouswaffles wrote:
               | >A pocket calculator that would give the right numbers
               | 99.7% of the time would be fairly useless.
               | 
               | Well that's great and all, but the vast majority of llm
               | use is not for stuff you can just pluck out a pocket
               | calculator (or run a similarly airtight deterministic
               | algorithm) for, so this is just a moot point.
               | 
               | People really need to let go of this obsession with a
               | perfect general intelligence that never makes errors. It
               | doesn't and has never existed besides in fiction.
        
         | robot-wrangler wrote:
         | I'll take a shot at it. Using collatz as the specific target
         | for investigating the underlying concepts here seems like a big
         | red-herring that's going to generate lots of confused takes. (I
         | guess it was done partly to have access to tons of precomputed
         | training data and partly to generate buzz. The title also seems
         | kind of poorly chosen and/or misleading)
         | 
         | Really the paper is about mechanistic interpretation and a few
         | results that are maybe surprising. First, the input
         | representation details (base) matters a lot. This is perhaps
         | very disappointing if you liked the idea of "let the models
         | work out the details, they see through the surface features to
         | the very core of things". Second, learning was burst'y with
         | discrete steps, not smooth improvement. This may or may not be
         | surprising or disappointing.. it depends how well you think you
         | can predict the stepping.
        
       | rikimaru0345 wrote:
       | Ok, I've read the paper and now I wonder, why did they stop at
       | the most interesting part?
       | 
       | They did all that work to figure out that learning "base
       | conversion" is the difficult thing for transformers. Great! But
       | then why not take that last remaining step to investigate why
       | that specifically is hard for transformers? And how to modify the
       | transformer architecture so that this becomes less hard / more
       | natural / "intuitive" for the network to learn?
        
         | embedding-shape wrote:
         | Why release one paper when you can release two? Easier to get
         | citations if you spread your efforts, and if you're lucky,
         | someone needs to reference both of them.
         | 
         | A more serious answer might be that it was simply out of scope
         | of what they set out to do, and they didn't want to fall for
         | scope-creep, which is easier said than done.
        
           | Y_Y wrote:
           | For interest, this popular pastime goes by several delicious
           | names: https://en.wikipedia.org/wiki/Least_publishable_unit
        
             | kkylin wrote:
             | :-)
             | 
             | I don't question this decision is sometimes (often) driven
             | by the need to increase publication count. (Which, in turn,
             | happens because people find it esaier to count papers than
             | read them.) But there is a counterpoint here, which is that
             | if you write say a 50-pager (not super common but also not
             | unusual in my area, applied math) and spread several
             | interesting results throughout, odds are good many things
             | in the middle will never see the light of day. Of course
             | one can organize the paper in a way to try to mitigate the
             | effects of this, but sometimes it is better and cleaner to
             | break a long paper into shorter pieces that people can
             | actually digest.
        
               | Y_Y wrote:
               | Well put. Nobody want salami slices, but nobody wants
               | _War and Peace_ , either (most of the time). Both are
               | problems, even if papers are more often too short than
               | too long.
        
               | godelski wrote:
               | Not only that but in the academic world 20 papers with 50
               | citations is worth more than one paper with 1000. Even
               | though the total citation count is the same the former
               | gives you an h-index of 20 (and an i-10 of 20) but the
               | latter only gives you an h-index of 1 (ditto for i-10).
               | 
               | Though truthfully it's hard to say what's better. All can
               | be hacked (a common way to hack citations is to publish
               | surveys. You also just get more by being at a prestigious
               | institution or being prestigious yourself). The metric is
               | really naive but it's common to use since actual
               | evaluating the merits of individual works is quite time
               | consuming and itself an incredibly noisy process. But
               | hey, publish or perish, am I right?[0]
               | 
               | [0] https://www.sciencealert.com/peter-higgs-says-he-
               | wouldn-t-ha...
        
             | senkora wrote:
             | Relevant SMBC: https://www.smbc-
             | comics.com/index.php?db=comics&id=1624
        
         | fiveMoreCents wrote:
         | cuz you don't sell nonsense in one piece. it used to be "repeat
         | a lie often enough" ... now lies are split into pieces ...
         | 
         | you'll see more of all that in the next few years.
         | 
         | but if you wanna stay in awe, at your age and further down the
         | road, don't ask questions like you just asked.
         | 
         | be patient and lean into the split.
         | 
         | brains/minds have been FUBARed. all that remains is buying into
         | the fake, all the way down to faking it when your own children
         | get swooped into it all.
         | 
         | "transformers" "know" and "tell" ... and people's favorite
         | cartoon characters will soon run hedge funds but the rest of
         | the world won't get their piece ... this has all gone too far
         | and to shit for no reason.
        
         | fcharton wrote:
         | Author, here. The paper is about the Collatz sequence, how
         | experiments with a transformer can point at interesting facts
         | about a complex mathematical phenomenon, and how, in supervised
         | math transformers, model predictions and errors can be
         | explained (this part is a follow-up to a similar paper about
         | GCD). From a ML research perspective, the interesting (but
         | surprising) take away is the particular way the long Collatz
         | function is learned: "one loop at a time".
         | 
         | To me, the base conversion is a side quest. We just wanted to
         | rule out this explanation for the model behavior. It may be
         | worth further investigation, but it won't be by us. Another
         | (less important) reason is paper length, if you want to submit
         | to peer reviewed outlets, you need to keep pages under a
         | certain number.
        
           | observationist wrote:
           | It might be a side quest, or it could be an elegant way to
           | frame a category of problems that are resistant to the ways
           | in which transformers can learn; in turn, by solving that
           | structural deficiency in order to enable a model to
           | effectively learn that category of problems, you might
           | empower a new leap in capabilities and power.
           | 
           | We're a handful of breakthroughs before models reach
           | superhuman levels across any and all domains of cognition.
           | It's clear that current architectures aren't going to be the
           | end-all solution, but all we need might simply be a handful
           | of well-posed categorical deficiencies that allow a smooth
           | transition past the current jagged frontiers.
        
           | godelski wrote:
           | I'm curious about 2 things.
           | 
           | 1) Why did you not test the standard Collatz sequence? I
           | would think that including that, as well as testing on Z+,
           | Z+\2Z, and 2Z+, would be a bit more informative (in addition
           | to what you've already done). Even though there's the trivial
           | step it could inform how much memorization the network is
           | doing. You do notice the model learns some shortcuts so I
           | think these could help confirm that and diagnose some of the
           | issues.
           | 
           | 2) Is there a specific reason for the cross attention?
           | 
           | Regardless, I think it is an interesting paper (these
           | wouldn't be criteria for rejection were I reviewing your
           | paper btw lol. I'm just curious about your thoughts here and
           | trying to understand better)
           | 
           | FWIW I think the side quest is actually pretty informative
           | here, though I agree it isn't the main point.
        
       | Onavo wrote:
       | Interesting, what about the old proof that neural networks can't
       | model arbitrary length sine waves?
        
         | kirubakaran wrote:
         | That proof only applies to fixed architecture feed forward
         | multilayer perceptrons with no recurrence, iirc. Transformers
         | are not that.
        
       | jebarker wrote:
       | This is an interesting paper and I like this kind of mechanistic
       | interpretability work - but I cannot figure out how the paper
       | title "Transformers know more than they can tell" relates to the
       | actual content. In this case what is it that they know and can't
       | tell?
        
         | godelski wrote:
         | I believe it's a reference to the paper "Language Models
         | (Mostly) Know What They Know".
         | 
         | There's definitely some link but I'd need to give this paper a
         | good read and refresh on the other to see how strong. But I
         | think your final sentence strengthens my suspicion
         | 
         | https://arxiv.org/abs/2207.05221
        
       ___________________________________________________________________
       (page generated 2025-12-09 23:01 UTC)