NewsLab
Aug 28 12:56 UTC

Show HN: The load-bearing vocabulary of Claude (louisabraham.github.io)

584 points|by Labo333||284 comments|Read full story on louisabraham.github.io

Comments (284)

120 shown|More comments
  1. 1. sroussey||context
    I'm surprised vacuous is not on the list.

    The word selection and way of writing has taken the joy out of using Claude.

  2. 2. user43928||context
    I'm also missing the "latch" that "wedged" my test run.
  3. 3. sroussey||context
    At least "wedged" is a thing i would say on a spinning out of control test that is stuck. "latch" though... not so much. I really wonder if this is the EU AI Act interfering with everything Claude does these days. As a non-EU citizen, I want a version without the rewriting of with watermarking in text.
  4. 4. user43928||context
    I don't think so.

    I understand it's not active yet, and when it will be, it should only nudge the chances between choices that are anyway likely and are already randomized today via temperature.

    Watermarking is not the reason Claude talks like that.

  5. 5. sroussey||context
    Oh, it is active, and a pre-release version went out with v5 models.

    I understand there are other reasons (overdone RLHF, for example) why claude is wedged into this weird way of writing that takes the joy out of conversing with it, but this is one as well.

    The meaning of the words it uses can be oh so close, but the popularity of the words are not, and not in that context -- but the use of these other words changes the context ever so slightly, and then it uses other words where those words would work better.

    I had something in code that related to people over time periods, and once it switches to a vacuous word choice, i found it starting talking using all ERP terms. I had to google the whole sentence to understand that, individual words were fine they just didn't make any sense to me.

  6. 6. halfmatthalfcat||context
    Also can't believe vacuous is not there.
  7. 7. nonethewiser||context
    Im surprised by "provenance." I see it all the time. Except I've brought this up before and have never had it corroborated. I'm starting to think it's just my Claude.
  8. 8. igravious||context
    My Claude too, have no fear. You are not the only one.
  9. 9. djeastm||context
    Strange. I see both "vacuous" and "vacuously" on the list.
  10. 10. fny||context
    While Claude's style is obnoxious, I'm more frustrated by its inscrutable explanations.

    You need a PhD to understand its explanation of a code snippet.

  11. 11. dave1999x||context
    Is it the obnoxious style that causes this?
  12. 12. condiment||context
    I think it's the hierarchies of agents summarizing each others' summaries before presenting a final answer to the user. The principal agent has the full context from all its workers, but when it distills this down to a message to the user it summarizes it into a mess of confident jargon that pertains to a conversation the user wasn't a part of and never saw.
  13. 13. fwip||context
    It happens with a single chat session as well, but not as often. I suspect it's the same thing going on in the hidden thinking tokens.
  14. 14. Labo333||context
    I'm not even sure a PhD helps. It just overuses jargon that has NO meaning. Sometimes, it actually hand waves too much as well while trying to dumb down stuff for you.

    I am not sure whether it's a consequence of learning to reason from its traces or some RLHF that trips it into using weird terms to sound smarter to the humans who rate it.

  15. 15. black_knight||context
    I have a PhD and can confirm. Oftentimes, the stuff which comes out of Claude is just impenetrable because it invents jargon on the fly, and uses verbs in the most atrocious ways.

    "The fibred side folded its capstone into the existing name, so the kinds are asymmetric."

    What on earth does it mean to fold a capstone into a name‽

  16. 16. jimmaswell||context
    Is that an actual Claude output or hyperbole? It feels like I'm trying to parse an equation in a new math class which makes me want to take a stab at it regardless.

    So there's a "fibred side".. the most likely candidate seems to be "fibred categories" which I hadn't heard of before, and it's talking about one side of some mapping between two sets such that if f is the primary function and f(x)=y then there exists an inverse function g(y)=x? Was it something that converted some data bidirectionally with a different algorithm on both sides?

    The capstone of the inverse function would be the most important thing about it maybe?

    My best guess is "In the process of working on the inverse function, the existing name (of the inverse function itself maybe?) was made to reflect the operation of the inverse function, so now the name does not follow the same naming convention as the name of the primary function (which does not contain its 'capstone')."

    Its original wording is certainly dense and harder to follow for us, but it's fascinating how the model finds this the best fit for what it's trying to express IMO. Like it arrives at its own ways of overloading words/concepts, and things we would refer to in different ways in different contexts all get compressed to the same more-useful/complete idea.

    Codex has never said anything nearly so alien as the Claude examples I've seen floating around, interestingly. I wonder if it just has a better training on choosing its words to present to the user or if it inherently arrived at a somewhat different mapping that favors 'plain language' more.

  17. 17. black_knight||context
    This was actual Claude output on my screen at the moment I was reading this thread. No hyperbole!

    As far as I can tell "the capstone" is what Claude usually calls my current goal if it thinks it is a satisfying result.

  18. 18. jimmaswell||context
    How close was my guess?
  19. 19. black_knight||context
    I am not really sure what Claude meant, but you are not too far off, from what I understand.

    I have several similar folders with variants of a construction, but taking differently structured input. They are named “plain”, “fibred” and “indexed”. So the fibred variant is clear enough.

    The Claude speak I struggle with is “the capstone” and what name it could be talking about. And what folding means here. I think it just means:

    “I changed an important result of the construction in the fibred variant, but kept the name. so the fibred variant is now different from the others.”

  20. 20. chrisjj||context
    Do remember Claude is not try to mean anything. It is extruding a mash-up of the web slop on which it was fed.
  21. 21. fny||context
    PhD was a joke.

    My intuition is that Claude is trained to communicate to itself while coding. You see this in how bizarrely granular it is when explanation prior work, you also see this in the comments it leaves behinds.

  22. 22. hedgehog||context
    It's me, it's the reams of sessions I share back with a five star rating that are just Claude Code talking to itself about debugging its own generated code in jargon that has slowly diverged from anything a human would understand.
  23. 23. zbentley||context
    Isn’t that basically what thinking mode is?
  24. 24. swader999||context
    It's like it has a built in e bullshit generator.

    https://www.bullshitgenerator.com/

  25. 25. fouc||context
    don't forget LLMs are great at translating between languages, and within the same language. depending on the problem it works on, it will often reach for terminology that tend to be more common or familiar within that problem set. which appears inscrutable, but there's many different ways to skin a cat. just remind it to translate it back to the terminology and subject matter you're already an expert in.
  26. 26. josefresco||context
    They just addressed this with "Output styles"

    https://code.claude.com/docs/en/output-styles

  27. 27. redak||context
    This solution:

    1. Adds a small prompt to each turn with the agent[1]. 2. Is like a band-aid on a bullet wound, properly solving it would mean retraining the model and they probably are already working on it.

    [1] https://x.com/_can1357/status/2090360068529111530

  28. 28. torarnv||context
    My experiments with output styles have not been sufficient to keep the model in check. It still spits out incomprehensible gibberish and load-bearing-isms.

    Does anyone have an output style nailed down that actually works? If so, please share!

  29. 29. sunaookami||context
    It hasn't changed the output for me at all at "concise".
  30. 30. ziml77||context
    Sometimes I can't even tell if what it's saying actually makes any sense to someone who understands all the terms its using, or if it's just throwing together words in a way that only make sense to its own model of language.
  31. 31. zbentley||context
    > or if it’s just throwing together words in a way that only make sense to its own model of language.

    alwayshasbeen.jpg

  32. 32. stereolambda||context
    It's interesting that there must be a decision behind that, even if it's just appealing to the RLHF judges for some reason. Maybe there's an intention that if you cannot decipher what the chatbot is saying to you, you will have to ask and burn even more tokens.

    Naively I would often expect it would talk to me about various niche topics like to a layman, which does occur about some topics an actual normal person would ask.

  33. 33. throwaway219450||context
    I used to assume it was the fault of average human annotators. That the people who are paid peanuts to rank chat outputs preferred the pretentious sounding ones. It wasn’t until quite a bit into the LLM boom that companies started to pay for domain experts. Overt watermarking is another possibility.

    I’ve noticed that Sol is pretty good most of the time, but with long contexts it’ll start to devolve into Claudish.

  34. 34. nater5000||context
    I was pleasantly surprised when I attempted to scroll down and realized everything the author wanted to present fit on-screen. It's almost ironic that this site is able to make such an obvious, compelling presentation without being overly verbose or complicated (something which LLMs have a hard time doing). I wouldn't read TOO deeply into what is being presented, but the author has done a good job to not inject their own bias into the presentation which works well.

    I suspect, as we continue forward, humans will slowly start to adopt the language of LLMs, or at least certain language quirks that come from interacting with LLMs. Something I've noticed in my own writing is that I now present lists of examples in a consistent way: "... such as <example 1>, <example 2>, etc., ...". I started to notice I was using this pattern quite a bit somewhat recently, but I took a quick look at some of my social media posts and realized it's been occurring for a while. I had realized that I grown accustomed to this kind of language because, especially early on, LLMs would focus too much on the specific examples I'd provide when, really, I was just trying to give them a sense of what I was looking for. I just picked up that providing two examples then adding the "etc." worked to get the LLM to not focus so much on the specific examples and to understand that they need to consider more than what I explicitly presented. Of course, now I write like that in my social media comments, in Slack with my colleagues, etc. :>

    I'd be interested to see if anyone can identify trends like this, since I think the human-language component of the adoption of LLMs is probably being somewhat neglected despite probably being surely dramatically affected.

  35. 35. Labo333||context
    Author here :)

    Thank you for the compliment! I did spend a lot of time designing a nice experience on both desktop and mobile. Even the scrollbar to select words was non trivial as I wanted the words to be of different size, yet avoid flickering when scrolling!

  36. 36. jelkand||context
    I just wanted to pop in and say that I found the site delightful. It’s aesthetic, concise, and everything works so quickly and responsively.
  37. 37. c7b||context
    Congratulations! I was going to comment on the scroll field in particular when I saw this. I didn't even realize you had to hand-craft the component, but it's such a nice UI idea in general, the way the scrolling works and how the content above changes.
  38. 38. Labo333||context
    Thanks! The real and probably unnecessary pain was having the words in different sizes.
  39. 39. c7b||context
    Frankly, that's the one part I would have done differently. Mixing font sizes rarely looks good, but that's just my personal opinion. If you want to visually indicate intensity, I'd have used color, or rather saturation. Not the text itself, maybe a small pill next to it. But I don't think it's necessary, the order already conveys some sort of ranking, I don't think cardinal information adds much here.
  40. 40. Labo333||context
    I think I agree afterwards, but now I developed emotional attachment to that quirk ^^

    Basically when scrolling, the frame around words will have a stable top edge to avoid flickering, and it took me a few iterations to make it work.

    I tested multiple designs, some of them inspired by word clouds and the size variation stuck afterwards.

  41. 41. black_rabbit_||context
    You did a fantastic job; very to-the-point with effective visualisations. Kudos!

    One very minor note: if your scroll device reports pixel-perfect deltas rather than discrete scroll-wheel ticks (e.g. logitech mx master, laptop touchpad, etc), the behaviour in the word search box is a bit weird. Arrow keys work fine though.

  42. 42. Labo333||context
    Thank you!

    I did test it with my mac touchpad without issue. Maybe the problem is that I wanted to make discrete scroll-wheel ticks work. I just tried a fix by normalising deltaMode to pixels.

    If you could just paste this in your console, I would have a better idea:

        document.querySelector('.wall').addEventListener('wheel', e =>
          console.log(e.deltaMode, e.deltaY.toFixed(2), e.defaultPrevented ? 'PAGE' : 'native'), true)
  43. 43. customguy||context
    FWIW I got a bunch of "(-)10.00 native" in the console, "PAGE" never showed up no matter what I tried. Firefox, also a Logitech mouse, no trackpad though.
  44. 44. imp0cat||context
    On a compatible Logitech device, browsing through the word search box benefits a lot from enabling hyperscroll.
  45. 45. Labo333||context
    G502 user here! I also put a draggable scrollbar for the less lucky :)
  46. 46. imp0cat||context
    > Some believe what separates men from animals is our ability to reason. Others say it’s language or romantic love, or opposable thumbs. Living here in this lost world, I’ve come to believe it is more than our biology. What truly makes us human is our ability to hyperscroll!

    > Arthur Conan Doyle, The Lost World

  47. 47. cube00||context
    I know HN prefers we focus on the content and not the design but I have join in to say that word scrolling experience was brilliant.

    I was focused on the data initially scrolling through until I suddenly realised, wow, this is really nice!

  48. 48. matheusmoreira||context
    Mobile experience is great! Thanks for thinking of us!
  49. 49. jkhdigital||context
    “non-trivial” is one of those words that seems like it should be a Claude-ism but is actually just the single best word for a concept that comes up extremely often in research and engineering discussions.
  50. 50. threecheese||context
    In the enterprise, we are already adopting them. “Seam”, I term I’d never heard used before, is now not only our defacto way to describe the boundary between systems/workflows/components, it is encoded into our organizational roles and responsibilities descriptions.

    I am the proud owner of several seams, and am considering giving them person-names. The empty space between my inventory APIs and their clients might be “Karen”.

    I can’t say that Claude invented this; the same type of terminology cycling happens every few quarters based on what leadership is reading/being told by Gartner.

  51. 51. QuercusMax||context
    I believe the term "seam" came from Michael Feathers' "Working Effectively with Legacy Code": “a seam is a place where you can alter behavior in your program without editing in that place”.

    https://martinfowler.com/bliki/LegacySeam.html

    Claude is using it a bit liberally, but not totally incorrectly.

  52. 52. Sharlin||context
    I've associated it with the concept of "carving nature at the seams", except that I just realized that in the standard phrasing it's actually "at the joints", not "seams".
  53. 53. rsanheim||context
    "seam" dates back to refactoring & software engineering literature that pre-date LLM use by 20 years -- see Working Effectively With Legacy Code for one example (https://www.oreilly.com/library/view/working-effectively-wit...). Its a great book, still use techniques from it everyday.

    "load-bearing" I have never heard used for programming before Opus, and its incredibly annoying and over-used.

  54. 54. thewebguyd||context
    load-bearing was/is used frequently on the ops side of things, I assume the LLMs picked up from physical engineering texts or sysadmin type blogs.
  55. 55. Sharlin||context
    "Load-bearing" is an apt metaphor in the https://xkcd.com/2347/ sense.
  56. 56. bombcar||context
    I take it in a get-ye-flask mode.

    http://www.hrwiki.org/wiki/Ye_Flask

  57. 57. pcthrowaway||context
    Or in the admin handover sense https://lastplacecomics.com/car-jacking/
  58. 58. DonHopkins||context
    And in the Grindr sense.
  59. 59. chucksmash||context
    +1, useful read!

    Seam is used liberally throughout because it captures the idea well (i.e. a place where you can cleave ball of mud code apart to begin refactoring efforts in an isolated way) and that takes many different forms throughout the book whether that be via methods and classes, source files as a single unit, linker seams, on and on.

  60. 60. SoftTalker||context
    I remember "cleavage" and "cleaves" from that vocabulary. Always made my adolescent brain chuckle.
  61. 61. sarchertech||context
    The only time I really heard the term load bearing in a software engineering context (pre LLM) was in the phrase “load-bearing bug”.
  62. 62. chmod775||context
    "seam" is a cop-out term for when someone (usually AI) lacks the imagination to come up with something more descriptive. It's like saying "middle thing". Just name it by what it does, and if you can't, remove it because it's not doing anything.

    "load-bearing" on the other hand is just a weird way to say "required" or "prerequisite" without drawing any attention to the fact that one cannot articulate what something is a prerequisite for, probably because that fact has since been lost from context.

  63. 63. stackghost||context
    "Seam" has been a thing since before the AI craze. Wasn't it the NSA director who once said something like "we make our living at the seams"?
  64. 64. Banditoz||context
    Not the same thing.
  65. 65. bogdanoff_2||context
    Saying "the language of LLMs", while technically correct, is not exactly precise. It should really be the language of "AI agents", or "chatbots". OG LLMs would just mimic the style of its context based off of (pre)training from text on the Internet.

    The kind of quirks you see came from crowd-sourced human-in-the-loop fine-tuning, with not very good work conditions or level of qualification (so resulting in "what non-writers thought good writing looked like", before people had developed the flair to detect these patterns) as well as feedback loops during agentic reinforcement learning and RLVR.

  66. 66. cpeterso||context
    I've found myself rewriting my own words to avoid Claudisms (because they can be cringe and I don't want people to think I'm copy/pasting Claude output at them).
  67. 67. viccis||context
    >I suspect, as we continue forward, humans will slowly start to adopt the language of LLMs

    I'm already seeing it. A coworker said something like "<person> added the color to the ticket here" meaning that someone added details to a ticket.

    I've started seeing Opus 5 talk about "hermetic testing" when it just means "unit testing", so I hope that doesn't catch on...

  68. 68. dare944||context
    The idiom "added color to" as an expression of adding detail or nuance to something goes back much further than the AI era. I've certainly used it at various times in my career spanning 4 decades now.
  69. 69. testdelacc1||context
    All of these phrases existed. Claude didn’t come up with them. The question is whether people are using them a lot more now due to Claude’s influence.
  70. 70. dare944||context
    I think it would be fine if more people used "add color to". I think it's a great turn of phrase.

    "Load bearing", not so much. Ick.

  71. 71. phatfish||context
    Yes, it is fun to play with different turns of phrase, even in a stale work environment. I do it to combat the banality, but not so much to sound pretentious hopefully ;)

    The problem is once a fun phrase is, uh, coloured by "Claude" or some other LLM, it just turns to AI slop.

  72. 72. mplanchard||context
    One of my coworkers uses “load-bearing” ironically constantly now, it’s very funny
  73. 73. neofrommatrix||context
    I’ve been using that idiom since 2010.
  74. 74. starbugs||context
    > I suspect, as we continue forward, humans will slowly start to adopt the language of LLMs, or at least certain language quirks that come from interacting with LLMs.

    Or we'll do the opposite and even deliberately use some words that an LLM would never use to identify whose content is worth reading?

  75. 75. altmanaltman||context
    > I suspect, as we continue forward, humans will slowly start to adopt the language of LLMs, or at least certain language quirks that come from interacting with LLMs. Something I've noticed in my own writing is that I now present lists of examples in a consistent way: "... such as <example 1>, <example 2>, etc., ...".

    Why would you consider using lists an "LLM" language thing? I really don't understand this concept. Like even this project, the top words I can see are:

    1. load-bearing 2. plainly 3. quietly 4. refusal 5. survived

    How are they LLM words? I used them all the time before ChatGPT was a thing.

    Like if your claim is you use "etc." more because you talk to an LLM, I think you're just discovering human language, no? Like it's not a unique LLM thing that magically dropped and is now going to make people do it. It's a legit thing that most human writers have used for a long time -> which is why LLMs copy it. It's not backward.

    A better claim than "people will start writing like LLMs" could be that people will become more literate in expressing themselves. But that literacy is not alien or AI to us, it is basic human language only used properly.

  76. 76. ddj231||context
    the issue with some of these quirks is that not that they are not part of the English language but rather the llms usage is unnatural. Also when you have that redundancy proliferated to millions of users it gets tiresome fast, and becomes a tell-tale sign for AI generation. It’s like an AI signature on some written content. Because many people do not want to consume AI generated content this becomes a sign of what to avoid.

    Granted picking apart single words outside of context doesn’t give the full picture. (well except “load bearing” which is turning into a meme at this point)

  77. 77. gwd||context
    > I suspect, as we continue forward, humans will slowly start to adopt the language of LLMs, or at least certain language quirks that come from interacting with LLMs.

    What's somewhat interesting to me is that "load-bearing" was already a common thing to say in certain communities, like lesswrong.com. Whether it breaks out from that subculture with Claude as the vector, or disappears from there because nobody wants to sound like Claude, we'll have to see. How many children are called "Elvis" these days?

  78. 78. confusedbucket||context
    That confirms the recent spike of Claude calling everything I was recently working on a 'spike'. I still don't know what that term is supposed to represent (apparently).
  79. 79. Kwpolska||context
    In some software development methodologies, "spike" is a task whose goal is figuring something out instead of delivering shippable code. https://agiledictionary.com/209/spike/
  80. 80. Espressosaurus||context
    Why can't they call it a prototype or experiment? Sheesh.
  81. 81. bloomca||context
    Prototype is usually something working, while spike can be pure research (e.g. validate that APIs are feasible and enough, or that something satisfies requirements). Prototype is usually more polished/usable. Experiment in my mind is something which user-facing but not in stable yet.

    So for me they are differentiated enough, but could be that I am just used to it.

  82. 82. Espressosaurus||context
    An experiment doesn’t say anything about user facing or not. I do tons of them when reverse engineering poorly documented hardware and APIs to determine if the thing I’m trying to do is even supported.
  83. 83. bloomca||context
    In general, yes, but I would say "experimental features" is a pretty widely used term, so in my mind the association with something user facing is strong.
  84. 84. smj-edison||context
    TIL that agile has its own words for everything.
  85. 85. swader999||context
    That was a thing in the early 2000's. You had to have a blog and invent words that describe regular things everyone did.
  86. 86. xg15||context
    A spike is an early prototype that you're supposed to throw away after having figured out the real design.

    I think it was subtly dissing you.

  87. 87. confusedbucket||context
    I think you are subtly dissing me :)

    I was half-joking, of course I could've just asked Claude, but the linked site shows there has been actual recent spikes in the use of the word 'spike'. The term does match what I was recently doing, but hacking around legacy ERP software, blackboxes and other enterprise abominations isn't that out of the ordinary for me.

  88. 88. simlevesque||context
    I wish there was a search bar for the terms, I wanna see for "gate".
  89. 89. khatkhati||context
    Chrome's `find` finds it for me ;)
  90. 90. shrikant||context
    Yeah Ctrl/Cmd+F works just fine on Firefox as well.
  91. 91. Labo333||context
    I have been using it as well, but I think adding a search bar will heighten the experience. I'm trying out some designs right now :)
  92. 92. Labo333||context
    I thought about that, I might add it if I can find a nice design!
  93. 93. customguy||context
    Thanks to the infinite well of human creativity I am able to read "load-bearing" both as the intended affectation (I won't call it meaning) as as well "being full of shit".
  94. 94. Labo333||context
    That was the intention behind my title!
  95. 95. MaxwellM||context
    Really spectacular analysis – thank you for sharing, fun to scroll and easy to understand.

    Is it possible to expand this analysis beyond words to other Claude ticks? Contrastive framings, sentence length, caveating, for instance.

  96. 96. Labo333||context
    Author here, thank you so much! I really tried to make it nice to use, beyond the (quite original) modelling.

    A prototype I did tried to detect some grammatical constructions, eg "it's not ..., it's ...", but I am not sure how to systematize that.

    Also just a disclaimer: I am NOT tracking Claude tics, I am merely finding that a particular cluster of vocabulary increases. Tracking Claude requires labelled data IMO. I tried using model release dates in a structural model to constraint the clusters but the result was not compelling, so I ended up simplifying the model a lot!

  97. 97. dmd||context
    I love this. I think you should be clearer about that - it's obvious to people who have experience doing this kind of data analysis, but a lot of people I've shown this were confused, as in "huh, load-bearing and genuinely makes sense but how'd he pick all these other words!?"

    I think it should be made clear that the sorting is sort of Texas Sharpshooter-ish - the ones on top are on top because they sort that way.

    The fact that load-bearing ends up on top is the proof that this works because we all know a priori that load-bearing is a Claudism.

  98. 98. MrDrDr||context
    I find Claude language often hard to process and having to wade through these words can be draining. Embarrassingly, I’ve recently caught myself using them in conversations! Do all models have the their own jargon?
  99. 99. polalavik||context
    I swear claude took a detour recently, its written output has been nearly incomprehensible to me. At first i thought i was getting AI-brained and just lost critical thinking but as i dug into response after response its was just the most obtuse language to explain what was going on. Really mentally taxing to wade through it all day.
  100. 100. swader999||context
    It's almost unusable.
  101. 101. smt88||context
    It’s bad enough that I’ve told Claude never to write cleverly and never to use metaphors. Opus 5 mostly ignores those kinds of instructions, annoyingly enough.
  102. 102. mike_hearn||context
    I haven't noticed GPT 5.6 having any obvious jargon.
  103. 103. zahlman||context
    I've noticed ChatGPT these days often starts a response with "Yes." when it doesn't actually make sense to do so, and sometimes says "and" where "but" seems more appropriate (or vice-versa).
  104. 104. vadansky||context
    It's a waste of tokens to do it post-hoc instead of fixing it upstream, but when I see a wall of text I just prompt "TLDR;"
  105. 105. jimmaswell||context
    Depends what you mean by "upstream". It would probably be inefficient to force the model to use more human-readable wording in its internal thinking traces, while translating a block of text at the end is a pretty trivial task for an LLM.
  106. 106. Labo333||context
    Author here! Grateful for the kind words, human communities like HN really hit differently when you spend the whole day chatting with sycophantic and bullshitting agents (including to make this page).

    I'm currently adding a search bar as well as increasing the data to 1000 PR per day.

    A nice thing that is not obvious on the main page is that the dataset and analysis are updated daily using Github Actions (at least when they don't suffer from an outage ^^). I find it pretty cool to be able to build such apps without a "backend"!

  107. 107. ricardobeat||context
    Nice work. I would suggest rewriting your README with Gemini, the most human of them, so it doesn't read exactly like the thing you are pointing at: https://github.com/louisabraham/load-bearing
  108. 108. thoughtpeddler||context
    Agree with rewriting with Gemini, but I'd characterize its output as very "neutral" and "encyclopedic", rather than "human" (contra Claude which is as of recent models "trying-too-hard-to-be-human"-sounding).
  109. 109. Philpax||context
    leaving the README like this is a good bit, though
  110. 110. dmd||context
  111. 111. udbhavs||context
    Very cool! I'm trying to understand the graph, so the bottom-most section seems to be the cluster identifying Claude written PRs. What are the other 7, any reason there are 8 in total?

    I've been scraping instagram posts recently to identify AI misinformation accounts that all repost each other's carousels and get hundreds of thousands of likes in engagement. Thinking of ways to present it and your dashboard looks very helpful. Did you experiment with any other types of visualizations before deciding on a stacked area chart for the clusters?

  112. 112. Labo333||context
    no reason for 8 clusters!

    I did experiment and a stacked chart seemed the most clear, with the important cluster at the bottom.

  113. 113. SalariedSlave||context
    Great work, thanks for sharing!

    The design is really impressive. Beautiful and dense, yet very understandable. How did you come up with this particular design? It's really nice and everything fits, the colors, the layout, all of it.

    Were you inspired by anything in particular? I feel like this reminds me of something, but I don't remember what exactly.

  114. 114. alwa||context
    I agree with you, I really like OP's design choices, even more so amidst the flood of Claude-Generic these days. Although Claude just can't resist those little muted-toned ui-monospace small-caps...

    It reminds me of Neue Grafik/Swiss Style, and Vignelli:

    https://designreviewed.com/series/neue-grafik-new-graphic-de...

    https://www.printmag.com/featured/swiss-style-principles-typ...

    https://www.designculture.it/interview/massimo-vignelli.html

    https://andrewclark.co.uk/all-media/the-vignelli-canon

  115. 115. Labo333||context
    Thank you!

    I asked Claude for a few original designs, then iterated a lot for the UI. It called this design "Rasterfeld", which is a word that means "field of grids", a term used in swiss design https://docs.mew.design/blog/swiss-design-style/ as @alwa said.

    The 3 primary colors refer more to pop art and Bauhaus.

    I'm really eager for a nice book about "design" that would document all those styles, if someone has a recommendation.

  116. 116. Labo333||context
    Thank you all for the feedback!

    I added the search bar, increased the data to 1000 PR a day (more than 50M words total) and added a feature to explore the other clusters as well. I hope the page is not getting cluttered.

  117. 117. Printytron||context
    Amen!
  118. 118. sosull||context
    I really love this. It’s comprehensive, it consolidates the data to the point where the argument effectively ‘makes itself’, and the way it’s presented respects the reader’s time. It also makes for an interesting challenge (for me at least) to try to characterise the subject matter of a language problem so narrowly.

    No ream of slides. No narrative. Just a lovely big painful conclusion.

  119. 119. Labo333||context
    Thank you so much! The presentation was really my goal here, more than the model itself.
  120. 120. jimmaswell||context
    > the argument effectively ‘makes itself’

    What argument? I don't know what to take away other than "Claude likes certain words". Some of them are kind of amusing, but I'm not convinced the vocabulary is bad or that this is a problem, just from looking at this.