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

211–220 of 249 posts

Re: Can AI design circuit boards yet?

#211

Post by smokel »

ninkendo wrote: post #121
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,…

My 2¢: When google trained a neural net on Go moves, using some text notation for them, with no other vocabulary of any kind, just predict the next go move, they noticed a representation of a Go board had essentially formed in the network, all on its own. It had never “seen” a go board, or had one explained, but they could map neuron states to go board squares pretty much 1:1. I truly think that LLM’s with hundreds o…

> It had never “seen” a go board, or had one explained

I assume that you are referring to AlphaGo or AlphaZero. In either case, this statement is not correct. Both algorithms most certainly know exactly what a go board looks like, and what the rules are.

In the case of AlphaZero, it initially did not know how to best play the game, or what strategy or tactics would work. But the connections between the neural network and the go board are hardcoded, by humans.

Re: Can AI design circuit boards yet?

#212

Post by laughing_man »

matherial wrote: post #63
Scene_Cast2 wrote: post #60

I found LLMs circa 4 months ago to be decent at textbook-style electronics, but they choke at anything nontrivial. They approach things like someone that knows the undergrad and grad textbooks, but has absolutely zero experience. No ability to answer questions such as "is this adequate", "do I need a LPF here", "how do I kill resonance without increasing impedance", etc. I'm guessing that this is due to a lack of RL…

Old textbooks. They love 741 op-amps, etc.

There is always a better choice than a 741 for new designs, but somehow people still use those things too.

Re: Can AI design circuit boards yet?

#213

Post by SequoiaHope »

Always42 wrote: post #141
SequoiaHope wrote: post #119

Earlier quoted context omitted.

The designs are in Kicad format, and the Kicad APIs are useful for Claude to work with. I would say that right now this involves a lot of knowledge about PCB design to do well, or for more detailed designs. However you might research how to design board for fabrication at JLCPCB and try something simple. Eg make a board with only LEDs in some pretty pattern and make it so you solder a raspberry pi Pico 2 to the board…

I have both Altium and Kicad experience. Can you explain further how you are setting up the AI to interface with KiCad? Is your AI having keyboard/mouse access or are you doing it only through API? Not familiar with Claude interface.

I have it convert Altium files to Kicad and then it uses the Kicad api to control things. If you give it encouragement it should be able to convert back to Altium by parsing the format and building a tool. Supposedly I have this built though I have not validated it. You can also ask it how it would do this and it will have ideas.

Re: Can AI design circuit boards yet?

#214

Post by SequoiaHope »

varispeed wrote: post #206
SequoiaHope wrote: post #119

Earlier quoted context omitted.

The designs are in Kicad format, and the Kicad APIs are useful for Claude to work with. I would say that right now this involves a lot of knowledge about PCB design to do well, or for more detailed designs. However you might research how to design board for fabrication at JLCPCB and try something simple. Eg make a board with only LEDs in some pretty pattern and make it so you solder a raspberry pi Pico 2 to the board…

Will it improve already routed board? I have one done ages ago. Works fine, but RAM can only do roughly a half bandwidth because of poorly laid traces. Could I tell AI to reroute them according to best practices?

Ya it can

Re: Can AI design circuit boards yet?

#215

Post by mariebks »

smokel wrote: post #211
ninkendo wrote: post #121

Earlier quoted context omitted.

My 2¢: When google trained a neural net on Go moves, using some text notation for them, with no other vocabulary of any kind, just predict the next go move, they noticed a representation of a Go board had essentially formed in the network, all on its own. It had never “seen” a go board, or had one explained, but they could map neuron states to go board squares pretty much 1:1. I truly think that LLM’s with hundreds o…

> It had never “seen” a go board, or had one explained I assume that you are referring to AlphaGo or AlphaZero. In either case, this statement is not correct. Both algorithms most certainly know exactly what a go board looks like, and what the rules are. In the case of AlphaZero, it initially did not know how to best play the game, or what strategy or tactics would work. But the connections between the neural network…

Incredibly, Muzero didn’t even know the rules, it figured them out from starting with random moves: https://deepmind.google/research/alphazero-and-muzero/

Re: Can AI design circuit boards yet?

#217

Post by dboreham »

abletonlive wrote: post #209
sethaurus wrote: post #130

Earlier quoted context omitted.

That's just derision, not an explanation. And it's a bad way to treat someone humbly trying to learn.

I'm just surprised that so many intellectuals on HN hang on to false models of reality for so long after that reality has been demonstrably destroyed. It's not humble at all. In fact it's the opposite, completely arrogant and stubborn. It's been obvious and demonstrated at least since the end of 2025 for anybody that used LLMs at any capacity without dismissing them. If you are still surprised that your model of real…

There are so many of these buried ostrich head posts that I suspect some sort of bot farming. Why such posts make money for someone, I'm not sure.

Re: Can AI design circuit boards yet?

#218

Post by 3dB »

a2ff6eeb0 wrote: post #112
SequoiaHope wrote: post #103

I have 15+ years of PCB design experience. Mostly hobby stuff but a fair amount of processional work. Kilowatt range brushless motor controllers, basic RF stuff, lots of microcontroller stuff. I had Fable design an LED earring. Rechargeable coin cell, RP2350 cpu, IMU, 45 addressable LEDs. It made two mistakes - missed the through holes on the coin cell holder footprint and made the center pad too small. I was able to…

It's exciting. How long do you think it's going to be when electrical engineering is mostly going to be about verification of AI designs, and what are the tools out there to enable that?

The verification problem for hardware is a couple of orders of magnitude harder than it is for software because there often (usually) is no 'right' solution. There is a balance of tradeoffs governed by several information sources including standards, company policies, design trade offs and engineer preferences. Software style 'Lint checks' will exist for basic things like functional correctness - e.g. verifying net connectivity. But many verifications for things like EMC, EMI, SI, PI and thermal require engineering judgement to balance tradeoffs.

We're building a verification loop for hardware at Engentica, with a focus initially on EMC/EMI, and I do think the problem is solvable. But it requires a harness with lots of built in solvers for the hardware vertical, and I don't think it's something that LLMs will crack on their own.

As engineers adopt AI to help build circuits more and more, I think hybrid AI/deterministic verification will only get more important.

Re: Can AI design circuit boards yet?

#219

Post by NishanStepak »

There was an earlier article in Live Science which was also in Popular Science where AI designed computer chips which a human being might not make. I am assuming this might happen eventually with circuit boards and other electronics as well. Artificial Intelligence is not like us, it does things differently and might come up with some different designs than we would think of.

https://www.livescience.com/technology/computing/humans-cann...

Post reply on HN