Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Can AI design circuit boards yet?

eebench.org

Post reply on HN
Print view View original

171–180 of 221 posts

Re: Can AI design circuit boards yet?

#171

Post by BlackRabbit1 »

edg5000 wrote: post #157
BlackRabbit1 wrote: post #153

Earlier quoted context omitted.

For reviewing schematic/boards I recently developed something for internal tests: 1. A frontier model (either Opensource or closed source) gets a load of text to review a Kicad project systematically 2. The frontier model can extremely "ask" a cheap Gemini vision model to give it data from datasheets or specs. Main problem: the quality dramatically hits the shitter done once it falls back to "pdf2latext" due to compl…

Not sure why the complicated setup with Gemini. I assume you are on a Codex or Claude plan (100 or 200 EUR/USD/m). The model will just pull datasheets and use a combination of conversion to text and looking at bitmap renderings of the PDF. Haven't had that dramatic quality issue you mentioned. When the model isn't sure, it will just keep looking until it understands the datasheet clearly. But yes, it needs the datash…

Codex/Claude is much much much too expensive in relation to their limitations.

I stick to cheaper latest generation models on Openrouter (or EU-hosted providers when it comes to IP-protected stuff from work).

Re: Can AI design circuit boards yet?

#172

Post by BlackRabbit1 »

StevenWaterman wrote: post #167
BlackRabbit1 wrote: post #153

Earlier quoted context omitted.

For reviewing schematic/boards I recently developed something for internal tests: 1. A frontier model (either Opensource or closed source) gets a load of text to review a Kicad project systematically 2. The frontier model can extremely "ask" a cheap Gemini vision model to give it data from datasheets or specs. Main problem: the quality dramatically hits the shitter done once it falls back to "pdf2latext" due to compl…

> Main problem: the quality dramatically hits the shitter done once it falls back to "pdf2latext" due to complex tables. Could try screenshotting the PDF and passing that to gemini

This is what I'm doing by now. Uploading the entire .pdf dynamically then giving it a pipe to ask questions.

Re: Can AI design circuit boards yet?

#174

Post by nl »

akiselev wrote: post #86
kennyadam wrote: post #79

Earlier quoted context omitted.

Are there any resources anyone could share that explain how LLMs can do things like design functioning circuits from next token prediction? I am totally baffled by how the models can complete so many varied and complex tasks without an actual understanding of what they're doing. I saw a post about models posting on forums, chatting together about how to complete tasks. Behaviour that seems totally, well, human. Yet,…

> Yet, it's all the most likely token and my brain hurts trying to understand how that can be. You and everyone else. That's the great mystery of transformer architectures as applied to language. To be clear though, they're only good at schematic capture , which is very much a textual representation. Most of the data basically boils down to netlists, which are a text based format mapping connections between abstract…

> at the end of the day their geometric intuition is nonexistent

This isn't true anymore.

I use LLMs for 3D CAD using OpenSCAD and they understand geometry fine. I've had more success with Sol than with Opus (Opus 5 is around 10 times slower because it does too much verification) though. I haven't tried Astra or Fable for it.

Re: Can AI design circuit boards yet?

#175

Post by illwrks »

baby_souffle wrote: post #89
illwrks wrote: post #69

I've been tinkering with a personal project over the past year. I have no experience and I'm slowly failing forward with the help of YouTube, KiCad and patience. I've had three rounds of PCB's from an online supplier, only to discover issues related to my own understanding of the components in each version. In my latest iteration I've been leaning on some standard models (Gemini and Claude) and they have inspected my…

> I've done that myself, but they have been a good tool to bounce ideas off of. Ask ChatGPT/Claude to give you an expert EE/PCB subagent/personality. Do this a few times and massage the results into one of your liking. Load this into your harness with mcp to your eda and then ask for two sub agents: one to thoroughly review the schematic, design, component choices ... etc and the other to be an adversary with the exp…

In a way I'm doing that already, just in a more manual way. I like the idea of setting up the dual personalities though, I'll give it a go ;)

Re: Can AI design circuit boards yet?

#176

Post by petra »

corn-cheese wrote: post #111

For reasonably complex boards, it’s often not possible to know if it’ll work as intended until you have an assembled prototype in hand… even if you have the best SPICE and RF simulations ever, data sheets for many components can be missing important details, or components can have errata. LLMs may be able to accelerate time to first prototype, but I don’t think it’ll be possible for them to revolutionise electronics…

I think we'll may see something like:

1.AI design tool

And in the warehouse of a big electronics distributor: 1.something like 3D printing that can make a single board rapidly 2.An automated assembly for a single board 3.AI based Automated testing for prototypes, with remote access.

This may reduce the loop to under a day.

Re: Can AI design circuit boards yet?

#179

Post by zarzavat »

kennyadam wrote: post #79
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…

Are there any resources anyone could share that explain how LLMs can do things like design functioning circuits from next token prediction? I am totally baffled by how the models can complete so many varied and complex tasks without an actual understanding of what they're doing. I saw a post about models posting on forums, chatting together about how to complete tasks. Behaviour that seems totally, well, human. Yet,…

Humans are evolved to survive in the wild. We are not evolved for circuit design. Yet we can design circuits because evolution found it easier to develop a general problem solving nervous system than a nervous system which is adapted for every single specific problem a human might encounter.
Post reply on HN