Can AI design circuit boards yet? • Hacker News Board

Re: Can AI design circuit boards yet?

#41

Post by codekansas » Fri, Sep 04, 2026, 9:10 PM UTC

krupan wrote: post #34

I'm confused. Who made this benchmark and why? It is fascinating to me that people are putting this much work into trying to measure and evaluate LLMs when we've never gone to this level for humans. Sounds like they also built a harness/feedback loop so the LLM knows if it's doing a good job? Again, why didn't anyone ever do this for human engineers?

Humans learn differently from LLMs. LLMs already contain most of the information they need to be able to do PCB layout from reading the entire internet, but they need this kind of fast feedback loop to learn how to extract and use that information in the right way. Humans learn to act at the same time they learn knowledge.

Re: Can AI design circuit boards yet?

#42

Post by napowderly » Fri, Sep 04, 2026, 9:11 PM UTC

rpcope1 wrote: post #7

Just as some anecdatum, I've tried this a couple of times over the last few years. 2024-2025, no body could generate anything of any sort of complexity, however maybe around the Opus 4.7 timeline, I tried having it generate some relatively simple and one slightly more complex circuit around 8-bit PIC micros, and was very pleasantly surprised. The schematics for simpler stuff is usually OK, often with some of the kind…

[dead]

Re: Can AI design circuit boards yet?

#43

Post by mschuster91 » Fri, Sep 04, 2026, 9:12 PM UTC

The submission reeks of LLM tells (especially the "UI" just looks straight like the usual Claude slop).

Anyway... the posed question reminds me of an anecdote I cannot find because Google is contaminated to hell and beyond, some researchers a decade ago let a machine-learning algorithm loose on an FPGA, and it "found" a design that worked but made no sense, because it exploited unique physical features of this specific chip.

Re: Can AI design circuit boards yet?

#44

Post by Legend2440 » Fri, Sep 04, 2026, 9:15 PM UTC

mschuster91 wrote: post #43

The submission reeks of LLM tells (especially the "UI" just looks straight like the usual Claude slop). Anyway... the posed question reminds me of an anecdote I cannot find because Google is contaminated to hell and beyond, some researchers a decade ago let a machine-learning algorithm loose on an FPGA, and it "found" a design that worked but made no sense, because it exploited unique physical features of this specif…

Sounds like you're talking about the FPGA evolution experiments Adrian Thompson and others did in the 1990s: https://evolvablehardware.org/history.html

Re: Can AI design circuit boards yet?

#45

Post by lexicality » Fri, Sep 04, 2026, 9:17 PM UTC

krupan wrote: post #34

I'm confused. Who made this benchmark and why? It is fascinating to me that people are putting this much work into trying to measure and evaluate LLMs when we've never gone to this level for humans. Sounds like they also built a harness/feedback loop so the LLM knows if it's doing a good job? Again, why didn't anyone ever do this for human engineers?

> I'm confused. Who made this benchmark and why?

It's a thinly veiled advert for Atopile. I don't know if it's a company behind it or just someone with a lot of money to spend on advertising since their about page (and docs) both 404, and the "packages" link sends you to a login screen that tries to unlock 1password. I guess claude can make circuit boards but not functioning websites?

Re: Can AI design circuit boards yet?

#46

Post by napowderly » Fri, Sep 04, 2026, 9:18 PM UTC

ChrisMarshallNY wrote: post #35

Interesting. AI may be pretty good at managing the gazillion different things that make up circuit boards. Frankly, I am surprised that it isn't already a solved problem, as we've had silicon compilers, for many years, and I always figured that IC design is more difficult than PCB.

I think the amount of reuse is a big difference. IC tools build on characterized cells with a lot of the rules already encoded. With PCBs, even when you're reusing a reference circuit, you're often manually carrying over the constraints and figuring out which layout decisions mattered. A lot of the engineering gets repeated rather than traveling with the design. That's something we're trying to improve with atopile.

Re: Can AI design circuit boards yet?

#47

Post by iopapa » Fri, Sep 04, 2026, 9:18 PM UTC

CyLith wrote: post #27

A personal data point: I had Claude Opus 4.8 design a fairly textbook circuit that outputs a monochrome image burned in an EEPROM over standard 640x480 VGA using only 74 series logic and GALs. It designed the circuit and GAL code, and I did the routing, and got it made through JLC for $6. After it came back, there was one error that was not caught, which I could blue-wire, and it works just fine otherwise. I was fair…

Claude is surprisingly good at discrete digital design with 74xxx, wonder what it trained on. Did you run it on anything else digital?

Re: Can AI design circuit boards yet?

#48

Post by mschuster91 » Fri, Sep 04, 2026, 9:18 PM UTC

Legend2440 wrote: post #44

mschuster91 wrote: post #43

The submission reeks of LLM tells (especially the "UI" just looks straight like the usual Claude slop). Anyway... the posed question reminds me of an anecdote I cannot find because Google is contaminated to hell and beyond, some researchers a decade ago let a machine-learning algorithm loose on an FPGA, and it "found" a design that worked but made no sense, because it exploited unique physical features of this specif…

Sounds like you're talking about the FPGA evolution experiments Adrian Thompson and others did in the 1990s: https://evolvablehardware.org/history.html

Indeed! With the keyword "evolving circuitry" I was able to find the blog post [1], with only one submission 8 years ago that barely got traction [2].

Thanks!

[1] https://www.damninteresting.com/on-the-origin-of-circuits/

[2] https://news.ycombinator.com/item?id=18099226

Re: Can AI design circuit boards yet?

#49

Post by Neywiny » Fri, Sep 04, 2026, 9:20 PM UTC

iopapa wrote: post #47

CyLith wrote: post #27

A personal data point: I had Claude Opus 4.8 design a fairly textbook circuit that outputs a monochrome image burned in an EEPROM over standard 640x480 VGA using only 74 series logic and GALs. It designed the circuit and GAL code, and I did the routing, and got it made through JLC for $6. After it came back, there was one error that was not caught, which I could blue-wire, and it works just fine otherwise. I was fair…

Claude is surprisingly good at discrete digital design with 74xxx, wonder what it trained on. Did you run it on anything else digital?

They're 60 years old. The amount of training data on them is endless. Books, textbooks, videos, blog posts. The problem is when you want you do something that doesn't have 60 years of freely available documentation of their functions and applications

Re: Can AI design circuit boards yet?

#50

Post by exe34 » Fri, Sep 04, 2026, 9:21 PM UTC

andrewchambers wrote: post #10

I think the new Astra computer use demos show that the models might be able to do things like inspection of real world objects if given a camera. Super excited to see real world feedback added into the agent loops we have gotten used to working with. Could you let the model print and test the circuit boards it is prototyping with a jig?

I don't know about pcbs but i gave chat gpt a picture of my window to help design a mesh screen frame to hold the feline hostage in, and it gave a fairly convincing impression of understanding what was going on, although at one point it thought the window swung inwards (it's an outie).