Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • I have a general question regarding 3d design using LLMs. My understanding is that all current applications have been trying to deal with 3d design/CAD as text/code. LLMs are clearly good at those but do you see this as the long term approch for 3d designs? do you see world models eventually evolving to produce 3d spaces or point clouds or CAD designs instead of doing video? is this approch explored? Congrats on the launch!
    by fkilaiwi
  • I strongly believe that by scaling up LLMs we will get there. I write about this here in more detail: https://adam.new/blog/bitter-lesson-ai-cad
    by zachdive
  • I've been using the OpenSCAD version of this for a while. This new release is a big upgrade! I wish it worked with my preferred CAD, FreeCAD. But this is neat!
    by elgertam
  • Sweet!
    by zachdive
  • What exactly is the use case for this? Just making pretty little 3d models?

    There are so many reasons why I, as an engineer, will never even attempt to use AI for mechanical design, that trying to list them all is about to give me an autistic screeching fit.

    Even if all I need is a simple little bracket or something, I can model that and know it's right much quicker than I can ask the AI to do it and then check it's work. There is no time savings here.

    Heck, for any of the stuff I need that is simple enough to plausibly ask AI to draw, I don't even bother to model in the first place, I would either sketch it with a pencil or just make the piece right off the top of my head.

    If it's more complicated than that, then my approach grows to include things like what stock I have available, what tooling, fixturing and machines are present, whether I can use any COTS hardware to simplify the design, the tolerancing scheme I want to use...and my output needs to include not just the model, but toleranced drawings and any other assemblies and such that are required.

    And besides all of that, and with love....OpenSCAD is a joke, and if you seriously try to tell me that "the best paradigm for CAD generation is to generate CAD as code", I cannot take you seriously.

    by incorene2
  • This doesn’t seem to be for machining CAD but more like stuff you would 3D print at home
    by echoangle
  • I remember thinking like this about software development several years ago.

    "AI will never be able to reason and write code as well as a human".

    I was terribly wrong. I assume you will end up being wrong about engineering too.

    by munksbeer
  • > I can model that and know it's right much quicker than I can ask the AI to do it and then check it's work.

    For me, this is the issue with all the AI stuff. The real work in what I do is figuring out what I want (requirements, constraints, design aesthetics etc.) and once that’s done, the rest is easy.

    Even for things like voice commands, I’d much rather use a computer than talk to it.

    by taneq
  • I agree openSCAD isn't anywhere near powerful enough for professional workflows. Hence why I framed this as AI TinkerCAD.

    However, you can drive any professional CAD software though code. As we drive Autodesk Fusion via python through agents.

    by zachdive
  • The most difficult thing about these projects is for me to consider why anyone would want to use words to describe a 3D object. How do you reference objects? Saying "Make the hole at the end of the bracket 3 mm and move it up" isn't going to cut it. How do you know which end of the bracket I mean, and which direction does up refer to? So then I'd have to be more precise in what I'm asking for, and structure my words carefully in order to....

    In 3D CAD, you click on it. It's completely unambiguous and it also doesn't take 10 seconds to interpret your prompt (because I saw this tool can also read images, but takes time to do so).

    by alnwlsn
  • "I need an engine mount for 1999 toyota land cruiser j90 for the 1kz-te engine with a manual gearbox. Can you generate me a cad to send to a company in China to 3d print it?"

    "Done — I've created a heavy-duty, fully parametric engine mount bracket that fits a typical four-bolt block pattern and a single-stud chassis isolator with an alignment pin, much like what the 1KZ-TE requires."

    I dont think it's even close :(

    PS. Your entry message should be "Madam, I'm Adam" ;)

    by lukasm
  • There's already a lack of information online for simple things like torque specs. I can't imagine that a skilled professional could design the engine mounts even with if they had all of the relevant context online.

    As far as I know, the way that these reproduction hardware companies operate is that they have physical cars that they can design around.

    I have a 1993 Subaru WRX and I needed to replace the coolant header tank because mine had a bunch of leaks. I ended buying one from a specialty fab shop in the UK and I had to make a few measurements for them because there was varying bolt spacing for GC8 Impreza models.

    by rockostrich
  • I find all current LLMs to have pretty poor spatial awareness. It is becoming better, but still very poor. How are you dealing with that? Got any special tricks, any advice?
    by murkt
  • My favorite spatial reasoning benchmark: https://minebench.ai/

    no tricks, I'd definitely be curious to know how much screenshots help

    by conradkay
  • I write about this in detail here: https://adam.new/blog/bitter-lesson-ai-cad

    This is improving greatly in recent model releases

    by zachdive
  • No matter how much I’ve experimented with similar text-to-image projects including this one - the LLMs still don’t fully understand the visual feedback loop, and the results are far from what expected. And it doesn’t matter how the task is described, whether there’s a reference, or even if there’s a part of a finished model that just needs to be integrated into another component - the resulting models may be visually close to what is required, but they are not technically accurate.
    by dmpanch
  • Could I see what you tried to generate?
    by zachdive
  • https://modelrift.com/blog/openscad-llm-benchmark/ LLMs are still weak at spatial reasoning, but it gets better. Check out modelrift.com for another alternative
    by jetter
  • Is CADAM also what's used for the commercial product adam.new? How did you manage to write all those plugins? If it is also CADAM isn't stuff getting lost in the Fusion/Solidworks/Onshape -> OpenSCAD -> back process? Do constraints and everything just seamlessly import/export?

    Some comments here mention tolerances/functional requirements. Do you think the LLM/screenshot loop will scale to that too? Maybe rendering subassemblies individually until they make sense? Still feels like a full functioning V8 engine block needs _a lot_ of ghost-view screenshots to verify it works. What's your thoughts on a "simulation" approach, since it's not aligned with your bitter-lesson-blog-post?

    Are you able to reveal more about what kind of traction you have? 10s/100s/1000s of companies?

    Very cool open source project, and thanks for sharing so much!

    by Doerge
  • The same principles of an agent writing cad as code and then visualing inspecting the output in a loop runs through all our products. Whilst CADAM uses OpenSCAD, Fusion uses Python, Onshape use FeatureScript etc..

    The majority of our enterprise traction is on our flagship product: https://adam.new/

    Here you can connect to your engineering software and use AI to generate:

    - CAD - Renderings - Slides for design review - BOM

    and much more!

    by zachdive
  • I'm pretty skeptical of AI products, but your onboarding and first design experience has been pretty awesome. I will definitely spend a bit more time experimenting with this
    by dgellow
  • Thanks!!
    by zachdive
  • damn credits are consumed fast. And they are pretty expensive, $20 for 2k credits won't last long at all
    by dgellow
  • Congratulations on the launch. The propeller demo looks good :) BTW, customising gears (which are then laser cut from sheet metal) is also a common request from untechnical people who need CAD help.

    How do you differentiate from other open source AI CAD solutions? I’ve also had a good experience with Claude Code and CadQuery, which is a Python toolkit for generating CAD designs based on OpenCascade. I.e. what’s your moat?

    And given that you’re YC funded .. what’s your plan for millions in MRR?

    I’m asking because I would like to launch some useful open source tools myself (but for PIM, not CAD) and I just can’t figure out how to make open source sustainable, let alone profitable enough for hockey stick revenue growth. Any tips? Book recommendations?

    by fxtentacle
  • To be completely honest CADAM is not at all a revenue driver for us. The majority of our customers are on our flagship app: https://adam.new/ which uses OpenCascade and allows you to connect to your CAD, PLM & PDM tools.

    We built CADAM largely to give back to community and support a tool for hobbyists and individuals.

    by zachdive
  • Can it work from photos? I'm specifically thinking about stuff like this:

    https://www.tooltrace.ai/

    by criddell
  • Yes it can! You can even use mesh mode which is very strong for this!
    by zachdive
  • Wow, that’s a solution to an oddly specific problem I didn’t know existed, but it looks kind of cool
    by echoangle
  • It did a great job with this prompt. Got it done in about the time it would take me to login and load Fusion. I forgot to include the wire diameter but it made a reasonable assumption and included it in the params for edits

    "Make a grommet seal for a hole in an aluminum pipe where a cable goes through. The hole is 0.48 inches in diameter. The wall of the pipe is .25 inches thick. Make the seal split so it can be installed with the cable in place. Make a circular cover lip that is .2 inches across on the outside, and an inner lip to secure it that is smaller. It will be printed in flexible tpu"

    by patja
  • nice!
    by zachdive