Settings

Theme

Tool book of a Nuremberg knight from 1505

loeffelholz-codex.org

170 points by edwardog · 115 comments

Reader

19 threads
dirk-loeffelguy

Hi, I'm Dirk - the person behind loeffelholz-codex.org.

First of all, I'd like to thank you all for taking the time to explore the project. And for the criticism. Some of it was pretty harsh, but much of it was fair.

You were right about the English texts. I originally created the site in German and used AI to help with the translation. I should have reviewed the results much more carefully. That's on me.

As you noticed, I used AI-generated images to imagine what the devices in Löffelholz's drawings might have looked like in real life. It seemed like a great idea at first, especially before I had found actual replicas and artifacts. To be honest, I thought some of them looked really pretty.

I wasn't trying to pass them off as real: They were always clearly labeled as AI-generated, but that wasn't the problem. Some of the original drawings have perspective errors, and the AI carried those errors over into realistic-looking renderings. In some cases, the devices couldn't have looked like that.

Having those images on the folio pages made the whole project look AI-generated. I can see that now. I removed them completely.

I'm also working through the English translations again. Quite a few revised pages are already live (through folio 24r), and there's more to do. I still appreciate feedback, especially when something doesn't read naturally or seems wrong.

A special thank you to everyone who spoke up for the project. I really appreciate that! Your encouragement helped me deal with some of the harsher comments.

kornork

Lots of comments about the general use of AI here, but in particular I think the AI renderings are counterproductive and especially misleading in this application.

The original drawings have ambiguities in them; they are well done but perspective and scale are off, and there are lots of questions about particular details of the drawings. The AI drawings simply take these particular questionable details and render them as "real."

There should be real life artifacts for many of these tools. LLMs can just as easily go search the web for images of those as create completely unreliable, fictional renderings of the same.

peri-cl

https://loeffelholz-codex.org/en/codex/f076r.html

Reading this in between studying information theory makes a good laugh. This is the most inefficient code I've ever heard of. It's basically unary.

(For background, the first popular optical telegraph wasn't created until ~300 years later, and used 98 visually-distinct coding symbols).

https://en.wikipedia.org/wiki/Chappe_telegraph#Coding_and_de...

jacquesm

The LLM aftertaste is terrible but the idea is very nice.

If it's worth doing, why not do it well? This is a tiny book by book standards and writing this text would be a matter of a few weeks at most. And that way it would be much more valuable (and less off-putting)

  • scrollop

    Perhaps he is busy, and this is a passion project.

    As he says, he doesn't have much time to research the entire book.

    You think he has "weeks" to write it up for others?

    I imagine there are thousands of interesting projects people are doing solo and can't be bothered creating website to share with others for.

    If AI can do this- fantastic! Let people moan if they can't see the positives of this. He's not trying to win an award or is paid to create a site for the public.

kreyenborgi

Would be interesting, but the ai images and writing makes me trust it less.

WillAdams

An early project on my CNC machine was a basic set of inside/outside calipers:

https://community.carbide3d.com/t/locking-register-calipers-...

It would be interesting to see what would be involved in making the digital files which would allow re-creating each of these objects.

  • jacquesm

    Wow. Well done! How did you do the markings? Do I understand it right that you also made the fasteners?

    Were the holes at the top routed or done by hand?

    • WillAdams

      I drew up the markings in Macromedia Freehand MX, exported as an EPS, opened that in Fontforge, made it into a font, then used F-Engrave to V-carve them.

      The fasteners were sourced from a local hardware store and modified w/ a hacksaw, a wire crimping tool which was just the right size to hold them, and a file.

      The holes and outline were cut using a CNC following G-code output by MakerCAM (a fork of the Flash file PartKam).

      That was a _long_ time ago, and the free software has gotten much better/easier, and these days I work for a company which makes integrated software for the CNC machines which we sell.

      • jacquesm

        Beautiful work. I should do some blog posts on metalworking. It's so satisfying. I very much miss my Canadian workshop (2 lathes, big one and a small one for precision stuff), saw, mill (Bridgeport clone), shaper, 8x4' plasma cutter, welding tools) , what I have now is so limited in comparison. Otoh it's fine, all those tools require a lot of upkeep and if you use them infrequently then that's a lot of overhead.

        I'd love to see more things you've made.

        • WillAdams

          I'm a corporate shill these days, so it's mostly on our official file-sharing site:

          https://cutrocket.com/u/WillAdams

          (and mostly wood/bamboo)

          A bit stalled because I've been working on:

          https://github.com/WillAdams/gcodepreview

          Though I will note that I got into small-scale and inexpensive CNC because I couldn't figure out how to fit a Bridgeport that was being sold locally for less than scrap value in working condition into my basement.

          I've been debating getting a lathe or making a Gingery Lathe or going the 3D print route:

          https://www.printables.com/model/1048400-open-lathe-v1

          • jacquesm

            I've found that everywhere I lived within a kilometer there also lives a guy who has a complete machine shop in their garage. The problem is to find that guy. But it is really more than a coincidence by now. And once you find that guy you usually also find a friend because machinists are almost without exception nice people.

            • WillAdams

              Same, although these days, all-too-often one learns of this when one sees a garage sale notice that the shop is being sold (picked up some pretty nice tools thus).

Gabriel54

I am very happy to see people make use of AI to do previously impractical work, but the quality of writing on this page sounds like a poorly written middle school research paper.

> Not a diary, not a family chronicle - a tool book.

> As reliable as it says on each page - no more and no less.

> Pages without a special note have been editorially reviewed: carefully checked and corrected.

This sounds like an extremely interesting topic but the lack of care in the presentation is disappointing.

  • cwillu

    “carefully checked and corrected” is also the sort of thing that llm's like to insert when you tell them to carefully check and correct in the prompt, and isn't otherwise really a natural thing to write.

    • jacquesm

      LLMs love all kinds of idioms that indicate quality work (even when it isn't): 'checked', 'correct/corrected', 'witnessed', 'works/working', 'verified', 'validated'. They overuse these to the point that they become flags rather than reassurances.

  • shevy-java

    > the quality of writing on this page sounds like a poorly written middle school research paper.

    But that is typical AI quality. It is a fancified Babelfish 2.0 translator.

    Some humans also use AI to "interact" with other humans. They don't seem to understand that this is a problem for some humans. When a human AI slops me, I stop all any every further interaction (assuming I can find out that this human did so. It is not always possible to find that out).

    • Gabriel54

      I don't like to frame it in terms of, "this person is using AI, so I am no longer interested in communicating", because it is not really the AI that is the problem. It is the lack of effort put into communication with another human. AI can be extremely helpful for some people (e.g., proofreading text if one's native language isn't English). But this use case is almost never a problem if done carefully because the original ideas were all there in the beginning.

      I focus my frustration on writing that is circular, vague, unnecessarily explanatory, etc. In my experience this is a symptom of the fact that there were no original ideas to begin with.

  • amelung

    Maybe this is because of the translation, I guess the author has written the non-English version first and then got it translated into English with AI, adding some additional explanations if necessary.

    • Gabriel54

      That thought certainly crossed my mind, but having worked with people using LLMs for this purpose successfully, this instead comes across as taking a simple idea and asking {model} to expand this two or three sentence idea into a web page.

  • scrollop

    It may be the translation, however, this project is a passion for him. I would guess the passion is the book itself, and though he wants to share his passion, I imagine creating the actual page for others is tedious compared to the work of discovering the book. I have had the same issue.

    If an AI can save you time so you can continue with your passion, I say go for it. No one has paid you to create the page, he's not vying for an award. If people are interested they can read it.

  • taylorfinley

    This [0] is my secret weapon against this kind of slop. Any time I see any of these markers I tell my agent to read this again. Works unreasonably well.

    [0] https://gist.githubusercontent.com/birep/bb865b2799d3f86d55f...

dustfinger

Can anyone tell me how they would have made the paper and the pigments used in the drawings (or would these be called paintings)? Is this water colour? Is it reasonable for me to make my own paper and paints following the same receipts that would have been used to make this book and its contents?

  • jacquesm

    Pigments are a rabbithole that will suck you in and spit you out 10 years later with arcane knowledge about grinding up various gemstones, drying plants and all manner of minerals such as clays and so on. You will also be exceptionally well traveled.

    If you're ever in the Netherlands I can recommend a visit to the Zaanse Schans where they have a mill[1] from the days when pigments were ground with windpower. You can see the colors and you'll have a better understanding of why Royal Blue[2] was Royal (because it was incredibly expensive to make a lasting blue pigment).

    Fascinating stuff.

    [1] https://www.verfmolendekat.com/nl/

    [2] https://en.wikipedia.org/wiki/Ultramarine

    • dustfinger

      Thank you for the links, I really appreciate that. I have never been to the Netherlands, but it is someplace I would love to travel one day.

      I imagine it would be a rabbit hole, but rabbit holes can be a lot of fun. I will have to work with the poor-man pigments though. No ultra expensive gemstone grinding for me :-).

      • jacquesm

        Poor man pigments: vegetable matter. You can get surprisingly far on that alone. Side effect warning: people may think you need burning at a stake or weighing.

        Good quality pestles can be found on flea markets, people hardly ever use them now so they don't appreciate what they've got.

  • dirk-loeffelguy

    I don't know how they made the paper or the ink. But there is a page in the codex, that talks about inks and coloring. And even contains a recipe for paint: https://loeffelholz-codex.org/en/codex/f049v.html There is also a link to a scientific paper from Doris Oltrogge with recipes from the middle ages. Also I would like to point you to "christopher schwarz milk paint" - just google it. Chris is the cofounder of Lost Art Press. They make books about old and lost knowlegde. In an interview a year ago he talked about milk paint. Seems he has figured out how they made it :)

    What I find fascinating about Löffelholz's drawings is how alive they look. I guess he used a pencil for sketching, then ink for the outlines, washes for coloring and shadows. Then bright white paint for highlights.

BlackRabbit1

The entire website looks heavily LLM written/analyzed - and I'm not talking of the design which I'm fine with.

This devalues the scientific value a lot because every line must be checked for correctness and source.

The book itself is very beautiful and I'm thankful for the high quality pictures.

  • moffers

    The author says in the introduction that a certain amount of the book is verified. Presence of LLM-use doesn’t inherently make something of less value.

    • wise_young_man

      In ways it does though. There are telltale signs of AI writing that once you see it across sites repeatedly, it starts to be annoying to find.

      Couple of immediate examples:

      - The Codex has 154 pages. 127 of them have been reviewed, 27 not yet. - Each of the 154 pages gets a page of its own.

      If an author doesn’t have time to write. Why should I give up my time to read?

      • scrollop

        Maybe he is translating to English. Maybe he is translating himself and this is an artifact of German.

        "If an author doesn’t have time to write. Why should I give up my time to read?"

        Perhaps he is taking the time to translate it for you, otherwise you'd have to do it yourself.

      • tropicalhunter

        Can you point to any of those in the linked text?

        • boredatoms

          Our job isnt to review the work of LLMs for free

        • albedoa

          You could simply read the linked text yourself. This is worse than asking someone to google something for you.

        • iamacyborg

          From the first tool page. Clearly LLM slop.

          > Löffelholz does not open his book with a showpiece. He opens it with a practical tool you can adjust: choose a size, clamp it, work.

        • jacquesm

          It's all over.

      • CamperBob2

        If an author doesn’t have time to write. Why should I give up my time to read?

        Because -- if the author is to be believed -- essentially no one bothered to look at this work at all before AI became available to help with it. I had certainly never heard of it before. Had you?

        That's the choice being offered. Not between "LLM slop" or "painstaking human authorship", but between something being done or nothing at all being done.

    • lionkor

      OBVIOUS presence of LLM-use devalues something to the point that you have to wonder why a human is in the loop at all

    • gradus_ad

      The problem with AI generated content is, it tells me you didn't care enough about the work to do it yourself. To understand it fully, to the point where you don't need or even want to hand the work off to an LLM.

      Interacting with AI content makes me feel like I'm consuming something that was created purely for engagement farming. Not that human created content wasn't for engagement farming, but noticing an AI tell breaks the suspension of disbelief in a way. It devalues the relationship between creator and consumer, so that genuine care is not being shared. It's like I'm a cow being milked on an industrial engagement farm.

      • davhern

        I don't think is about caring or not caring, you can care about an idea but not have time or resources to work, or lack the technical knowledge. I have plenty of experience (10+ years) but my coding time is very limited, does that mean that I care less? No, just that I don't have time enough to code.

        I'm not pro AI by any means and I don't like the way this tech is turning the world into, but I see this as a people's problem, AI is a tool, the problem is how is being shoved into everything. Is nothing else than abstraction on top of another level of abstraction.

        Being an engineer is about finding the best way to solve the issue at hand. Your client won't care if you use to code AI, or if you use Javascript, or C#, Java,... your client will care that the issue at hand is fixed on the best possible way. Fix the issue fast and you'll have a happy client.

      • scrollop

        *

        1 point by scrollop 0 minutes ago | parent | next | edit | delete [–]

        "The problem with AI generated content is, it tells me you didn't care enough about the work to do it yourself."

        It may be the translation, however, this project is a passion for him. I would guess the passion is the book itself, and though he wants to share his passion, I imagine creating the actual page for others is tedious compared to the work of discovering the book. I have had the same issue.

        If an AI can save you time so you can continue with your passion, I say go for it. No one has paid you to create the page, he's not vying for an award. If people are interested they can read it.

        There are likely many people out there doing remarkable work but they can't be bothered creating a website to share with others.

        If AI can do that, fantastic - even though some people will moan. There are always people who complain.

      • esseph

        > It's like I'm a cow being milked on an industrial engagement farm.

        Always were, just now this signal makes people aware of it and they don't like how it makes them feel.

      • doug_durham

        Wow. This is the exact opposite of what that the site is. It is very clear that the author of the web site cares deeply about the material and has put a lot of effort into the work. You are letting your personal biases color your view. That is your right, but check to see if it is making you happy.

        • jacquesm

          Note that (1) this is just your opinion and (2) that he has put a lot less effort into it than others have put into similar endeavors which as a result have a different level of authenticity.

          > You are letting your personal biases color your view. That is your right, but check to see if it is making you happy.

          Why the free psycho analysis? GP just made a statement.

      • yababa_y

        [flagged]

        • dang

          Please don't cross into personal attack, regardless of how wrong someone is or you feel they are.

          https://news.ycombinator.com/newsguidelines.html

        • bloqs

          I suppose the implication is that you cannot presume human care with evidence of LLM use, it's considerably more likely that it's an indicator of lack of care, unfortunately.

          It's like saying "but a lot of human care goes into factory made X" when comparing it to handmade X. It starts on a lesser footing unless evidence suggests otherwise

        • criddell

          If you are deciding to delegate parts to AI, that’s probably a signal that it should just be edited out. If it isn’t worth your time to create, it probably isn’t worth my time to read.

        • boredatoms

          Any amount of slop makes the whole thing feel fake

        • QuantumNomad_

          There’s nothing delusional about what he said.

          AI is being used for the most part to shit out as much “content” as possible in order to show ads, sell courses and other products (bonus points if what is sold is itself also pure AI slop), or to finish tasks at work with as little effort as can be done, so that boss man is impressed by the velocity. “Who cares about quality? This is 2026, bro.”

          The actual thoughtful use of AI is the minority case. Not the default. We humans are lazy, and when we can get away with less effort we put as little effort as we can into things.

    • Gabriel54

      Using AI to go through an old manuscript has nothing to do with writing up those same results with AI. These are completely separate concerns.

    • lelandfe

      Is the author qualified to verify this book?

  • katzenq

    I at least appreciate the warning on unreviewed generated pages and excluding them from SEO until reviewed, but it's still all untrustworthy spam by default.

  • amelung

    OTOH, it also seems to draw much from https://kdih.badw.de/datenbank/handschrift/49a/4/1 according to the information on "Sources", which sounds genuine.

  • MOARDONGZPLZ

    There was one the other day. Seemed really compelling. History thing where they walked through a statistical life of a regular person at some point in history. Really enjoyed it until I realized the whole thing was basically ai slop. Totally devalued real work for some slop BS. So frustrating.

  • vehemenz

    There are, in fact, countless late medieval manuscripts just like this one. LLMs have been trained on many of them.

    What scientific value are you looking for?

tarheels100

I don't quite understand the degree of negativity given this is someone's personal project. They state that English is not their native language, so it's reasonable to me to leverage machine translation tools. For a work in progress, it seems good and I'm glad they are able to share it. You have to start somewhere, and getting it out there helps get more people involved.

  • stronglikedan

    We're still in the AI-use-is-black-and-white phase. Most people still think it's more than just a tool still, cuz it still seems like magic to them. We'll get there, and then it will just be a tool like any other. Hopefully then we'll start holding the people behind it accountable when appropriate, instead of allowing it to be used as a scapegoat, as if it has agency.

YrRight2PushBac

As interesting as this appears, I've developed such a strong allergy to LLM writing that I simply cannot consume any of this content

jimmySixDOF

for back in the day this knight had pretty decent 3D perspective rendering skills I mean you can knock the chair but there are a lot worse illustrations and devotional art from the time.

starkeeper

One thing that is mildly interesting about AI writing style is that all the major models use the exact same style. It is pretty foul smelling.

shevy-java

The knights did not have to deal with AI back then. It must have been a simpler life.

  • jacquesm

    Definitely, but also shorter and a lot more violent. And then there were the diseases...

intended

I wouldn’t know if the whole thing was AI or not at a glance.

giantfrog

Imagine going to a history museum and there’s a sign outside that says “Some of the information here is totally made up”

  • pronghorn

    You'd have to first get past the crowds of people outside talking about how bad the picture frames are.

starkeeper

Such AI Prose Wow. It's Not A fucking horrible writing it's an abhorrent word spasm.

suboto

TAG: VIBECODED

ithkai92

The author is transparent about the use of AI, but so many negative connotations in the site!!

      >I still have not found a place where truly every page of the Codex is described      and interpreted in detail. I want to change that. But as a single person, I can only take on a project this big with AI as a tool.
  • jacquesm

    > But as a single person, I can only take on a project this big with AI as a tool.

    That's so not true though. One of my uncles did work like this and it usually took a year or two to fully research a project and write a book but it is definitely doable to do this sort of thing - and much better, frankly - as a single individual. AI makes it a matter of days, but it also makes it next to worthless.

    The biggest contribution here is to make an otherwise lesser known book more known.

    https://de.wikipedia.org/wiki/L%C3%B6ffelholz-Codex

    (Couldn't find an English wikipedia page on it)

    • kreyenborgi

      Now that AI exists, doing things properly has become impossible for humans.

      • jacquesm

        Well you'll get exactly what happened here: you put in the word, do the research and make the content, then some AI jockey will come along and make a mashup and pass it off as their own.

  • lelandfe

    Or enlist others or do a little bit at a time or…

  • Planktonne

    The knight who wrote it took on a larger project without AI or a computer at all.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection