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

Testing Generative AI for Circuit Board Design

blog.jitx.com

Post reply on HN
Print view View original

61–70 of 180 posts

Re: Testing Generative AI for Circuit Board Design

#61

Post by seveibar »

I work on generative AI for circuit board design with tscircuit, IMO it's definitely going to be the dominant form of bootstrapping or combining circuit designs in the near future (Most people are wrong that AI won't be able to do this soon. The same way you can't expect an AI to generate a website in assembly, but you CAN expect it to generate a website with React/tailwind, you can't expect an AI to generate circuits without having strong functional blocks to work with.

Great work from the author studying existing solutions/models- I'll post some of my findings soon as well! The more you play with it, the more inevitable it feels!

Re: Testing Generative AI for Circuit Board Design

#62

Post by HanClinto »

pton_xd wrote: post #58
HanClinto wrote: post #27

Earlier quoted context omitted.

> But I think there's also the bitter lesson to be learned here: many times people say LLMs won't do well on a task, they are often surprised either immediately or a few months later. Heh. This is very true. I think perhaps the thing I'm most amazed by is that simple next-token prediction seems to work unreasonably well for a great many tasks. I just don't know how well that will scale into more complex tasks. With s…

> If you present a simple chess board to an LLM or a complex board to an LLM and ask it to generate the next move, it always responds in the same amount of time. Is that true, especially if you ask it to think step-by-step? I would think the model has certain associations for simple/common board states and different ones for complex/uncommon states, and when you ask it to think step-by-step it will explain the associ…

> > If you present a simple chess board to an LLM or a complex board to an LLM and ask it to generate the next move, it always responds in the same amount of time.

> Is that true, especially if you ask it to think step-by-step?

That's fair -- there's a lot of room to grow in this area.

If the LLM has been trained to operate with running internal-monologue, then I believe they will operate better. I think this definitely needs to be explored more -- from what little I understand of this research, the results are sporadically promising, but getting something like ReAct (or other, similar structures) to work consistently is something I don't think I've seen yet.

Re: Testing Generative AI for Circuit Board Design

#63

Post by HanClinto »

omgJustTest wrote: post #31
HanClinto wrote: post #14

This feels like an excellent demonstration of the limitation of zero-shot LLMs. It feels like the wrong way to approach this. I'm no expert in the matter, but for "holistic" things (where there are a lot of cross-connections and inter-dependencies) it feels like a diffusion-based generative structure would be better-suited than next-token-prediction. I've felt this way about poetry-generation, and I feel like it migh…

I asked this question of Duncan Dec 22! If you are interested I highly recommend this + your favorite llm. It does not do everything but is far superior to some highly expensive tools, in flexibility and repeatability. https://github.com/devbisme/skidl

This tool looks really powerful, thanks for the link!

One thing I've been personally really intrigued by is the possibility of using self-play and adversarial learning as a way to advance beyond our current stage of imitation-only LLMs.

Having a strong rules-based framework to be able to be able to measure quality and correctness of solutions is necessary for any RL training setup to proceed. I think that skidl could be a really nice framework to be part of an RL-trained LLM's curriculum!

I've written down a bunch of thoughts [1] on using games or code-generation in an adversarial training setup, but I could see circuit design being a good training ground as well!

* [1] https://github.com/HanClinto/MENTAT

Re: Testing Generative AI for Circuit Board Design

#64

Post by hadlock »

DHaldane wrote: post #54
neltnerb wrote: post #40

Earlier quoted context omitted.

I think the only bit that looked handy in there would be if it could parse PDF datasheets and help you sort them by some hidden parameter. If I give it 100 datasheets for microphones it really should be able to sort them by mechanical height. Maybe I'm too optimistic. The number of times I've had to entirely redo a circuit because of one misplaced connection, yeah, none of those circuits worked for any price before I…

Agree that PDF digesting was the most useful. I think Gemini could definitely do that microphone study. Good test case! I remember spending 8 hours on DigiKey in the bad old times, looking for an audio jack that was 0.5mm shorter.

As I understand it, PDF digestion/manipulation (and particularly translation) has long been a top request from businesses, based on conversations I've had with people selling the technology, so it doesn't surprise me that Gemini excels at this task.

Re: Testing Generative AI for Circuit Board Design

#65

Post by exe34 »

surfingdino wrote: post #45
HanClinto wrote: post #14

This feels like an excellent demonstration of the limitation of zero-shot LLMs. It feels like the wrong way to approach this. I'm no expert in the matter, but for "holistic" things (where there are a lot of cross-connections and inter-dependencies) it feels like a diffusion-based generative structure would be better-suited than next-token-prediction. I've felt this way about poetry-generation, and I feel like it migh…

> This feels like an excellent demonstration of the limitation of zero-shot LLMs. It feels like the wrong way to approach this. There is one posted on HN every week. How many more do we need to accept the fact this tech is not what it is sold at and we are bored waiting for it get good? I am not say "get better", because it keeps getting better, but somehow doesn't get good.

how long does it take for a child to start doing surgery? publishing novel theorems? how long has the humble transformer been around?

Re: Testing Generative AI for Circuit Board Design

#66

Post by HanClinto »

seveibar wrote: post #61

I work on generative AI for circuit board design with tscircuit, IMO it's definitely going to be the dominant form of bootstrapping or combining circuit designs in the near future ( Most people are wrong that AI won't be able to do this soon. The same way you can't expect an AI to generate a website in assembly, but you CAN expect it to generate a website with React/tailwind, you can't expect an AI to generate circui…

I'd be interested in reading more of your findings!

Are you able to accomplish this with prompt-engineering, or are you doing fine-tuning of LLMs / custom-trained models?

Re: Testing Generative AI for Circuit Board Design

#67

Post by oscillonoscope »

scld wrote: post #50
LeifCarrotson wrote: post #38

Earlier quoted context omitted.

Really? Most of the time? I find I spend an enormous amount of time on boring stuff like connecting VCC and ground with appropriate decoupling caps, tying output pins from one IC to the input pins on the other, creating library parts from data sheets, etc. There's a handful of interesting problems in any good project where the abstraction breaks down and you have to prove your worth. But a ton of time gets spent on t…

"Looks like you forgot pullups on your i2c lines" would be worth a big monthly subscription hahaha.

There are schematic analysis tools which do that now just based on the netlist

Re: Testing Generative AI for Circuit Board Design

#68

Post by oscillonoscope »

AdamH12113 wrote: post #33

The conclusions are very optimistic given the results. The LLMs: * Failed to properly understand and respond to the requirements for component selection, which were already pretty generic. * Succeeded in parsing the pinout for an IC but produced an incomplete footprint with incorrect dimensions. * Added extra components to a parsed reference schematic. * Produced very basic errors in a description of filter topologie…

I don't know enough about LLMs to understand if its feasible or not but it seems like it would be useful to make certain tasks hard-coded or add some fundamental constraints on it. Like when making footprints, it should always check that the number of pads is never less than the number of schematic symbol pins. Otherwise, the AI just feels like your worst coworker

Re: Testing Generative AI for Circuit Board Design

#69

Post by AdamH12113 »

bmicraft wrote: post #43
cjk2 wrote: post #23

Earlier quoted context omitted.

Make two separate signals arrive at exactly the same time on two 50 ohm transmission lines that start and end next to each other and go around a right hand bend. At 3.8GHz. Edit: no VSWR constraint. Can add that later :) Edit 2: oh or design a board for a simple 100Mohm input instrumentation amplifier which knows what a guard ring is and how badly the solder mask will screw it up :)

It would seem to me that the majority of boards would be a lot more forgiving. Are you saying you wouldn't be impressed if it could do only say 70% of board designs completely?

Not the GP, but as an EE I can tell you that the majority of boards are not forgiving. One bad connection or one wrong component often means the circuit just doesn't work. One bad footprint often means the board is worthless.

On top of that, making an AI that can regurgitate simple textbook circuits and connect them together in reasonable ways is only the first step towards a much more difficult goal. More subtle problems in electronics design are all about context-dependent interactions between systems.

Post reply on HN