Amateur may have cracked Linear A, a 120-year-old puzzle

(aiclambake.com)

267 points | by Kosturdistan 4 hours ago

20 comments

  • stratocumulus0 2 hours ago
    As an amateur who's been fascinated by this puzzle himself, I will add some context that might be relevant in assessing the plausibility of this claim:

    - The "Libation Formula", which the author used as the base for his translations, is the most studied piece of writing in Linear A, because it's the only recurring phrase (with grammatical variation) that we have. The corpus is extremely fragmentary, with just a handful of instances of longer text (and even then, the texts are the length of an average sentence in English). The majority of documents available to us are lists (of inventory, personnel, offerings or something of this sort). The longer texts make use of punctuation marks, likely put in between words. This gives us a non-trivial vocabulary, which still does not match that of any known language.

    - With such fragmentary remaining material, we cannot be sure that a) all the texts we call "Linear A" are written in the same language, and b) the recognizable words are not abbreviations, for example.

    - The author made an assumption that Linear A symbols which have counterparts in Linear B should have the same phonetic values. This gives us an already known glyph that represented "NA". "Duplicate" glyphs are only found in the P-series, and are assumed to represent syllables which were distinguished by the Linear A language, but not by Greek - such as aspirated/unaspirated P. There is a glyph that stands for "NWA" in Linear B, but instances of it have been found in Linear A as well.

    - There are countless words with no known etymology in Ancient Greek, assumed to originate from a substrate language or languages spoken in the area at the time Greeks migrated to their present-day homeland. The language of Linear A would be a likely candidate for such substrate. If Linear A were a Semitic language, then we should already be able to establish Semitic etymologies for those words as they were in Greek. Of course it could also be the case that these words came from an another language which did not adopt writing or its writing did not survive to our times.

    • tamarru 1 hour ago
      Ciao. I'm Tom di Mino, and I'm on vacation in Bellingham, Washington right now. I'll get back to you later with a formal response.

      I've also reached out to Dr. Ester Salgarella, so I'm familiar with attempts to apply computational analysis to the corpus, and where previous efforts erred.

      • stratocumulus0 43 minutes ago
        Always glad to exchange! I'm a software engineer and a hobby linguist only myself, so don't expect wonders from me. But this is a fun topic to research for sure.
      • Kosturdistan 39 minutes ago
        Tom has entered the chat!
    • _alternator_ 1 hour ago
      Thanks for the context; how do you think this impacts plausibility? Presumably the fact that he made progress in a well studied passage is cause for skepticism? What's your take?
      • yorwba 59 minutes ago
        Well, the reasoning in the article is that if you take A-TA-I-*301-WA-JA, keep only W-J and assume *301 starts with N, then you get a claimed Semitic root N-W-Y related to dwelling, except I wonder whether that shouldn't be N-W-H instead https://en.wiktionary.org/wiki/%D7%A0%D7%95%D7%95%D7%94 (Semitic isn't my area) so at best one fifth of one word matches two thirds of another therefore iT mUsT bE sEmItIc. A serious attempt at decipherment should at least try to explain the A-TA-I, or any of the other words in the sentence, for that matter.
  • simonw 49 minutes ago
    > Di Mino used Claude Code to build a suite of Python scripts that query, cross-reference, and organize the digitized Linear A corpus (drawn from the GORILA and SigLA databases), enabling systematic hypothesis testing at a scale that would have been impractical to do manually.

    That's exactly the kind of thing I'd hope Claude would be used for in these kinds of projects - building tools, not black-box "solving" the problem.

  • Kosturdistan 4 hours ago
    A lot of loonies make this claim, but Tom's work is credible enough that it's being reviewed by linguistics experts at Rutgers and Cambridge. Additional validation: his approach produces results. He's translated over 300 words, and that's never been done before, and his solution actually solves some problems in Linear B. Tom is an AI engineer, and Claude Code was key to his work. Disclosures: I know Tom socially, and I wrote the post at the link.
    • kubb 3 hours ago
      Let's wait until it's been verified.
      • gus_massa 45 minutes ago
        I agree. The post has too few information. Also

        >> reviewed by linguistics experts at Rutgers and Cambridge.

        Here in Argentina, near 2005, we had like 5 guys that claimed to have 5 independent solutions of the Goldbach Conjeture. Each one got a PhD student that volunteer to read it, discussed the obvious problems with the author, tried to help to solve them and after a few months of back and forth they concluded that none of the solutions were correct or has an interesting insight. Nobody was surprised about the that, but some wanted to give them a try.

        Until there is a official report by Rutgers or Cambridge, it doesn't mean too much.

        >> He's translated over 300 words

        Where is the table of translations?

        • Kosturdistan 28 minutes ago
          Skepticism is appropriate until the experts bless the work. I will point out however that all of the words Tom has translated provide strong support for his proposed phonetic values. And that's why I published the information prior to confirmation, along with the appropriate caveats.
      • mikestorrent 2 hours ago
        You're absolutely right! We've opened a ticket with the Linear A folks, hopefully they'll get back to us soon with an update as to whether we've got it correct or not. Hang tight!
        • kridsdale1 2 hours ago
          This comment sure is load bearing.
          • mikestorrent 2 hours ago
            It's the veritable smoking gun
          • TeMPOraL 2 hours ago
            Regardless, we should stand ready, loaded for bear.
        • saagarjha 2 hours ago
          A Linear ticket, hopefully
      • bawolff 1 hour ago
        How does an expert even verify something like this?
        • red_admiral 43 minutes ago
          They verified Linear B against a new tablet that turned up in a dig after the Kober/Ventris* solution had been published. It had pictures of jars with no or one or two handles, and the claimed Linear B for "two handled jar" and such next to the correct picture.

          * Ventris' publication, but given Kober's contribution to the work they should really share equal credit. I like to think Kober would have got there on her own if she had access to the larger corpus that Ventris had (the Pylos tablets) and a comparable amount of free time and money available.

        • pfdietz 26 minutes ago
          Linear A/B testing?
        • Kosturdistan 1 hour ago
          You look at the proposed sound values and compare it to other known languages. Languages from the same family share grammar and vocabulary.
        • sigbottle 1 hour ago
          I mean it's not like anyone could objectively go back in time and query ancient civilizations for what they meant, but presumably it means the verification heuristics, they have currently, pragmatic success, and expert solidarity means that it is "verified"
    • yorwba 3 hours ago
      Then why is there no link to the actual write-up?
      • Kosturdistan 1 hour ago
        The only write-up at the moment is my blog post, hopefully that changes in the coming weeks.
        • Sniffnoy 1 hour ago
          The blog post mentions a draft of a manuscript though. I was expecting something like a preprint. He's not willing to post that draft yet?
          • Kosturdistan 47 minutes ago
            I have seen and read his draft article, he's not comfortable sharing it publicly yet since it's being reviewed by experts.
            • ahknight 28 minutes ago
              But the Internet nerds wish to blindly judge something they know nothing about so they can feel better with the assumption that they could have done better somehow. How will they be appeased if the document they will say they have read and understood (without having done either) is not available to point at? How, I ask?!
      • GavinMcG 3 hours ago
        Presumably because it hasn’t yet been published?
      • m0llusk 3 hours ago
        It seems this is still extremely early in the process. There is an apparent finding that was shared. Evidence which would be the basis for a paper is "being reviewed by linguistics experts at Rutgers and Cambridge". So they are trying to do the right thing by talking about what they believe they have done but holding off publication and serious claims until later. The general idea that written forms can be categorized by systems built with Claude could be applied to other as yet undecipherable languages could be used by other interested investigators just with what is discussed here.
        • sillysaurusx 3 hours ago
          > The general idea that written forms can be categorized by systems built with Claude could be applied to other as yet undecipherable languages could be used by other interested investigators just with what is discussed here.

          Could you rephrase this or explain it more thoroughly? I don’t follow. What does it mean to categorize a written form by systems built with Claude?

          • tyingq 3 hours ago
            The same pattern/tech is generic enough that it might be able to solve other unrelated, and so-far undecipherable, written languages.
      • kelseyfrog 3 hours ago
        You can use Claude, like the author, to reproduce the result.
        • _verandaguy 3 hours ago
          This isn't really a reasonable approach, is it?

          The original prompts aren't provided, nor is the original context; even then, you can't really treat a stochastic system like an LLM as a major component in reproducibility.

          • ben_w 2 hours ago
            > even then, you can't really treat a stochastic system like an LLM as a major component in reproducibility.

            If you had the other things, being "stochastic" is not even remotely a show-stopper. Stochastic processes abound and are the reason the mathematics of statistics was developed in the first place, ultimately allowing us to create such things as LLMs.

            When all the relevant steps gets published, I absolutely expect a lot of people to (attempt to) reproduce this work even though LLMs are stochastic.

            • _verandaguy 2 hours ago
              My issue with this is that it's a form of "soft" reproducibility, where it'll work for many (maybe even most!) people, but that depends on the way the original prompt was formulated (read on) and the state of the random noise in the system.

              On the prompt formulation; prompts with very similar formulations (in terms of both semantics, hamming distance, or both) can lead to _wildly divergent_ outputs in my experience. It's not rigourous, and when that divergence happens, it's extremely difficult (arguably impossible, by nature of the architecture of transformers) to identify why the divergence happened and where.

          • Kosturdistan 1 hour ago
            Claude code was used to organize the material and to run simulations. The simulations were to determine the likelihood that the text was Semitic vs Tom got lucky. Tom has assigned probabilities to each of the syllables he has proposed sound values for.
          • fragmede 2 hours ago
            Sure it is. We're humans, not robots (well, I think I am, and I presume you are as well, but for all we know, we could be living in a simulation), so if the non-deterministic system decides to generate code that calls the variable foo one day and bar the next, as long as the code still does what's being asked of it, why do I care that the non deterministic system chose to call the variable something different when run on Tuesday? There's the computer science definition of determinism and the engineering result of "does it work", which are at odds. It's like the halting problem. We haven't solved the computer science definition of the halting problem, but give some C code with a loop that won't terminate to Claude, and it'll call that out as not halting.
            • _verandaguy 2 hours ago
              All things aside, I think this misses the forest for the trees on the halting problem.

              It's not about being able to throw claude or codex at a loop and having it evaluate it for halting, it's about being able to do this for arbitrary code. Computer science rigourously defines the halting problem as not computable and undecidable. within the framework of using something akin to static analysis using any deterministic Turing machine.

              There's not really a question of "solving" the halting problem like there's some as-yet unknown way of generally figuring out if arbitraty code halts. Turing proposed a proof in 1937 in favour of undecidability of what we now know as the halting problem, building on ideas first articulated by Church a few years prior.

              Frankly, if anything, it's reasonable to say that the halting problem's been solved, just in the direction of undecidability rather than decidability.

              Anyway, back to LLMs; as code gets more complex, the robot will need a bigger context window, more hardware resources, and more time, all of which will be variable due to the noise inherent in the system. It'll be difficult to put a useful upper and lower bound on how much computing power and time it'll take to figure out if a program ever halts. Which is all a bit moot, frankly, in the context of halting, but useful to keep in mind in the more general context of using these things as analysis tools.

          • iwontberude 2 hours ago
            Actually it is because Claude did the work and being a lay person isn’t really that high of a bar.
            • Kosturdistan 1 hour ago
              Claude helped, but did not do the work. This was a human dude who had a very helpful assist from Claude
          • TeMPOraL 2 hours ago
            > stochastic system

            Every day when you lower your butt onto your chair, you trust a stochastic system enough to assume you'll rest on the chair safely and not spontaneously phase through, which would lead to rather gory and painful terminal experience.

            Physics at macro scale is stochastic, which is a good reminder that stochastic != uniformly random. Expected distributions matter.

            • ben_w 56 minutes ago
              While strictly true, QM has such small standard deviations as to be irrelevant on the macro for things like bums and chairs.

              IMO a better example would be the stochastic nature of quality control in manufacturing.

              • TeMPOraL 20 minutes ago
                > QM has such small standard deviations as to be irrelevant on the macro for things like bums and chairs

                I was going to segue into thermodynamics as a backup example, but you made me think of something better.

                > IMO a better example would be the stochastic nature of quality control in manufacturing.

                How about, more specifically, food manufacturing? Or maybe, let's talk about cooking?

                Cooking is as stochastic as it gets, and we handle it fine. It could be better - the better version is called "chemical process engineering", it's what cooking looks like when you care about quality and consistency of output, and can afford the equipment and process actually necessary for it. Regular people don't (i.e. neither care, nor can afford) - we call this cooking. It's an art, not a science, and people not only do it, but love it, and tie their identities to it, and build businesses around it, and a culture that embraces all the compromises (and calls the more serious approach "unhealthy").

        • atrus 3 hours ago
          somehow I suspect it was a bit more involved than: Claude, please solve Linear A.
          • fragmede 2 hours ago
            A little bit more. If you ask ChatGPT to "solve linear a" it thinks you mean linear algebra. If you specify that it's the Minoan translation problem, you get a table similar to the one that we get a glimpse of in the without access to the paper, we can't say how much more work the paper has than my gist.

            https://gist.github.com/fragmede/bbf277d36a2398065f109484f34...

          • smsm42 2 hours ago
            You also have to add "make no mistakes"!
          • Kosturdistan 1 hour ago
            You are correct!
        • justin_dash 3 hours ago
          Unless if it was done by Fable!
          • kelseyfrog 3 hours ago
            The 'major insight' described in the article predates Fable's release by two week four days. It would be a complicated timeline.
    • grey-area 3 hours ago
      Amazing work and refreshing to see a well written and cogent post to summarise it. Would love to hear more about how he used Claude to help solve the puzzle.
    • dwroberts 2 hours ago
      You know him socially but is there a reason you’re writing this rather than him? It looks like he has his own web presence.

      Cynical read would be you’re stealing his thunder a bit by prematurely announcing this before it’s fully confirmed

      • jstanley 2 hours ago
        Promoting your friends' work is hardly stealing their thunder. It's increasing their thunder!
      • Kosturdistan 1 hour ago
        Tom knows I'm a freelance writer and decided to give me the scoop. He's more interested in linguistics than he is in journalism.
      • Conscat 2 hours ago
        Isn't it customary for the author of a post shared on HN to leave a comment on the thread?
        • dwroberts 2 hours ago
          I’m not referring to the parent comment: The post is not written by the author of the claimed breakthrough.
      • iwontberude 2 hours ago
        What thunder? Claude did the work and used a human to interface with experience and causality better.
        • Kosturdistan 1 hour ago
          Claude helped, it did not do the work. It would have taken Tom more time to crack on his own, and it would have been harder, but the key insights were Tom's not Claude's.
        • ben_w 2 hours ago
          The thunder is as per the headline. Assuming it passes review.

          One of the things I find weird with AI is how the dismissals of work that involve AI splits into two camps: like yours, saying the AI did the work while the human played no role and deserves no credit; and those saying the AI rips off its training data while the human using it played no role and deserves no credit.

          • iwontberude 2 hours ago
            I exist in both camps. Claude can’t launder human achievement into a different person. Claude stole it, but it’s still in Claude’s possession and is not transferable in any durable sense.
            • ben_w 2 hours ago
              > Claude stole it, but it’s still in Claude’s possession and is not transferable in any durable sense.

              No human, individually or as a team, has been able to solve this to date.

              To the extent this was Claude solving it itself and thus denying Di Mino any thunder, there was nobody to have stolen anything from. To the extent he has thunder to be stolen, it wasn't ever in Claude's possession.

            • timschmidt 1 hour ago
              Everything is a Remix: https://www.youtube.com/watch?v=X9RYuvPCQUA

              Either all information is stolen, or none is. Can't have it both ways.

  • Tuna-Fish 2 hours ago
    The reason linear A is so difficult is that the total remaining corpus of Linear A text is ~7500 characters, spread out over ~1500 inscriptions.

    If you have a 4k screen, you can fit all remaining Linear A text on your screen at once, in 14pt high font.

    • stratocumulus0 2 hours ago
      An in addition to that, a vast majority of documents are lists which consist of a "header" (1 to 3 words) and word-number pairs afterwards. An another common class are small clay seals with 1, 2 characters carved into them. It's likely that in both cases, we may be dealing with abbreviations.

      Some of the lists end with "ku-ro" and a number that's the sum of all the previous numbers, oddly frequently off by one.

      • humodz 1 hour ago
        It would be amusing if archaeologists in the future also end up spending countless hours trying to decipher my shopping lists and poor math skills
      • _kst_ 2 hours ago
        They hadn't yet decided whether to count from 0 or from 1.
        • cwmma 1 hour ago
          Surprisingly this comes up more then you'd think, for instance in Ancient Rome, tomorrow is two days away so all the dates are off by one from what you'd think it was. They mainly count down and it goes, 5, 4, 3, day before, day.
          • codebaobab 44 minutes ago
            I noticed that when I read Tom Holland's new translation of The Lives of the Caesars. All the dates were in the form "N days before Kalends/Ides".
        • kps 1 hour ago
          “Should array indices start at 0 or 1? My compromise of 0.5 was rejected without, I thought, proper consideration.” — Stan Kelly-Bootle (first person to obtain a postgraduate degree in computer science)
      • red_admiral 51 minutes ago
        ku-ro obviously means "carry in" :)
        • vidarh 32 minutes ago
          My French teacher told me a story of a Norwegian man who married a French woman. A few months after she'd moved to Norway, my French teacher had come to visit thrm.

          When she was leaving, the woman said "pose, pose". My French teacher was puzzled, and asked why she'd said that, and the woman asked if it didn't mean "au revoir" in Norwegian?

          Because it was what the cashier at the grocery store said to her every time.

          It means (carrier) bag.

    • dehrmann 2 hours ago
      Very vaguely, it makes it like a one-time pad where it can be anything you want it to be. Not quite, but so little text leaves a lot of options open.
      • AaronAPU 1 hour ago
        I wonder, is there a form of analysis which lets you quantify how ambiguous a set of symbols is? Maybe related to entropy?

        Obviously one symbol can mean literally anything, but you could also have very long strings of symbols with many different meanings.

        • red_admiral 49 minutes ago
          Yes. Somewhere in Claude Shannon's work, called the "unicity distance".
    • WithinReason 2 hours ago
      As observed by archaeologist John Younger, the entire Linear A corpus takes up only 1.84 pages of letter paper when typeset in 12 point font and 1-inch margins.
    • elbasti 1 hour ago
      I would love to have this image available!
      • tclancy 1 hour ago
        I’d send it to you but you probably wouldn’t understand it.
    • stringfood 2 hours ago
      when I first read the title thought he was talking about linear algebra and I was like damn it's not that hard
  • loudmax 2 hours ago
    This is very exciting. Congrats to Tom on the accomplishment.

    To be clear, this is an attempt at a decipherment. This is not proven, and we shouldn't consider Linear A to be "solved" until experts in the field have reviewed the work. In fact, it probably shouldn't be considered "proof" unless some more Linear A writings are uncovered and these are congruent with the method proposed. All that can be said for certain at this point is that this is an interesting conjecture.

    But this is a story worth following. This could be the real deal. More research and validation should follow and we should have a better idea in the next few weeks or months whether Linear A has really been solved. At the very least, this is an interesting attempt, and optimistically, it could yield real insight into Minoan culture. Kudos.

    • Kosturdistan 1 hour ago
      Thanks, I hope Tom is right, but now it's in the hands of the pros.
  • cwmma 1 hour ago
    Isn't a big problem with Linear A that there are so few symbols you can "solve" it relatively straightforwardly with no way to tell if you it's correct or not?
    • Kosturdistan 45 minutes ago
      The lack of discovered inscriptions does make deciphering it harder, but it is possible!
  • rich_sasha 1 hour ago
    Gotta love the nominative determinism: Tom Di Mino ("of Mino"?) cracks a Minoan language.
  • mNovak 2 hours ago
    Interesting writeup. Would be nice to have a couple images of Linear A/B scripts to visualize. Looking on google, they're very daunting!
    • Blahah 1 hour ago
      lineara.xyz is your friend
  • bazoom42 1 hour ago
    I wonder how you would even know if you have “cracked” it, given the corpus is so small?
    • Kosturdistan 44 minutes ago
      You know you have cracked it because using the proposed system you are able to translate the uncracked language. Also helpful if your proposed system for Linear A makes sense relative to related languages that are not Linear A. Tom's proposed phonetic values work for more than one language.
      • bazoom42 25 minutes ago
        Not questioning the particular finding, just wondering in general. E.g when linear B or hieroglyphs were cracked, you could check angainst other untranslated texts and see if the translation still made sense.
  • WhitneyLand 2 hours ago
    If confirmed this is really cool and impressive work.

    Honestly curious how many years before it can be one shotted in a coding harness with Fable.next by someone who’s not a linguistics expert.

    Develop, test, and rank hypotheses about the phonetic values, morphology, grammar, and possible language family of Linear A using the full available corpus. Do not assume any decipherment is correct. Treat all candidate readings as hypotheses to be scored…

    • danishanish 55 minutes ago
      I don’t imagine a model capable of the first part would require being told not to assume a decipherment is correct
  • vb-8448 2 hours ago
    I wonder if LLMs trained specifically for this purpose can perform well with "forgotten languages".

    I know I'm simplifying a lot, but all this deciphering isn't it just some kind of pattern matching?

  • doubleorseven 2 hours ago
    crossing my fingers for this guy.

    however, nawaya or what ever examples around it are not part of the Hebrew language.

  • indiv0 2 hours ago
    Can I get his decipher-forgotten-ancient-text skill? I want to try my hand at the Voynich Manuscript
  • evilfred 1 hour ago
    i'm gonna write a blog post now about how my buddy discovered cold fusion and will have a paper out real soon now
  • NooneAtAll3 2 hours ago
    relevant xkcd: https://xkcd.com/2151/
    • gorjusborg 8 minutes ago
      Wow, there really is an XKCD for everything.
  • OutOfHere 3 hours ago
    Is this extendible to a generalizable approach to translate any language pair (without a translation map or translation dataset)?
    • retrac 2 hours ago
      I think it is an open question: can an unknown language be cracked -- without any dictionary or grammar or understanding of the language? Just lots and lots of texts, maybe some of it bilingual.

      It's a common misconception that is what happened with Ancient Egyptian with the Rosetta Stone. The Rosetta Stone was just one of the big pieces of the puzzle. The decoding came when people realized that Coptic (a language written alphabetically and still in use in the Coptic Church today) is actually descended from Ancient Egyptian; as Spanish is to Latin, Coptic is to Ancient Egyptian.

      Similarly the attempts to decode classical Maya were all dead ends. Until Yuri Knorozov realized that it encoded the ancestor of the Maya languages which are still spoken to this day. (Knorozov's Wikipedia article is worth checking out just for his photo with his cat. [0] IMHO.)

      I have written before about the La Mojarra 1 stele in Mexico [1]. It looks a lot like Maya. [2] But it isn't Maya. Maybe the difference like between Russian and Latin writing?

      No one can read it. It's undecipherable. There are some attempts to identify it with a proposed ancient language that would have been related to the modern Mixe-Zoque languages: some of the glyphs that are shared with Maya, when read phonetically, start sounding like a Mixe-Zoque language. But no one has proposed a confident decipherment. There probably isn't enough text. La Mojarra 1 is the only long example of the Isthmian script.

      Deciphering Akkadian was very difficult, at first. The process started with Persian; old Persian was written in a simplified adapted form of the Mesopotamian cuneiform (wedges on clay). It was a kind of alphabet. And Old Persian was already understood. And there was a bilingual text on a monument carved by Darius I. But even then -- decoding relies so heavily on the fact that Akkadian is a Semitic language distantly related to Hebrew, more distantly, also Ancient Egyptian. So again, we sort of knew what we were looking for.

      That is all to say: even if the Voynich manuscript (for example) contains real text in an otherwise completely lost language, I'm not sure it is possible even theoretically to translate it.

      [0] https://en.wikipedia.org/wiki/Yuri_Knorozov

      [1] https://en.wikipedia.org/wiki/La_Mojarra_Stela_1

      [2] https://commons.wikimedia.org/wiki/File:La_Mojarra_Stela_1_S...

    • Kosturdistan 1 hour ago
      Tom thinks he may be able to use his approach to crack more languages, but that's not confirmed.
    • SoftTalker 2 hours ago
      Towards the Star Trek universal translator.....
  • rw_panic0_0 2 hours ago
    would like to hear more about Tom's learning/education path in ML/AI.
    • Kosturdistan 1 hour ago
      I haven't talked to him extensively about how he learned his engineering skills, but he is I believe 100% self taught. His background is in copywriting.
  • pfdietz 23 minutes ago
    Now get to work on Harappan.
  • fooster 2 hours ago
    Alot of the comments in this thread are disappointing. Rather that celebrating an achievement (whether or it is validated yet), many of you seem to want to put him down, or make it seem like claude did all the work.

    Claiming that claude did all the work is patently ridiculous. Claude is a tool, like any other. The corpus of linear A is ~7500 characters across ~1500 inscriptions and claude, no matter how smart, doesn't just solve that on its own.

    What a shame.

    • evilfred 1 hour ago
      this isn't an achievement, it's yet another amateur crank claiming he solved a famous puzzle, without a paper and without any critical review. many people have claimed to decode Linear A before. just because this guy used an LLM doesn't make it more credible
      • Kosturdistan 41 minutes ago
        He has a working draft of a manuscript that may form the basis of a scholarly article, it has been shared with experts, and there is an excerpt of the paper in my blog post. I have also seen and read the paper with my own 2 eys, I can't publish it though, Tom wants to keep that under wraps while it's reviewed by linguistics experts.
        • BigTTYGothGF 2 minutes ago
          > He has a working draft of a manuscript that may form the basis of a scholarly article, it has been shared with experts

          So did many of the previous attempted solvers.

        • evilfred 12 minutes ago
          the info provided is completely unverifiable.
    • tennfown 1 hour ago
      [flagged]
  • iwontberude 2 hours ago
    Sorry but I don’t recognize this as being an achievement by an amateur. This dude had no chance in hell until we trained a model to use his time to suss it out.
    • jonahx 2 hours ago
      Assuming this pans out, every other professional linguist in the world has had the option to use Claude or other LLMs, but has not solved this problem, despite the incentives for doing so. It stands to reason the human is adding crucial value.
    • Kosturdistan 1 hour ago
      I drilled down on this with Tom. He thinks that it might not have happened without Claude Code, but Claude was used to organize all of the symbols, and to run I think it was 100,000 simulations to assess whether or not he had an actual insight, or if he just randomly got lucky. Claude did NOT crack the code. Significant supporting role though.
      • BretonForearm 1 hour ago
        So Claude Code was used to generate software that ran simulations? I don't think LLMs in and of themselves can execute simulations, esp. a specific, non-single digit count like 100k.
        • Kosturdistan 14 minutes ago
          I don't know if the agent ran the simulations or if the agent built software that ran the simulations. But Claude was used to run the simulations.