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

31–40 of 180 posts

Re: Testing Generative AI for Circuit Board Design

#31

Post by omgJustTest »

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

Re: Testing Generative AI for Circuit Board Design

#32

Post by netsec_burn »

stavros wrote: post #16
imperio59 wrote: post #4

Earlier quoted context omitted.

That's because the sample size is probably small and for niche prompts or topics. It's very hard to evaluate whether a model is better than another, especially doing it in a scientifically sound way is time consuming and hard. This is why I find these types of comments like "model X is so much better than model Y" to be about as useful as "chocolate ice cream is so much better than vanilla"

True, I just tried it for generating a book summary, and Sonnet 3.5 was very bad. GPT-4o is equally bad at that , gpt-4-turbo is great.

This more likely has to do with context length?

Re: Testing Generative AI for Circuit Board Design

#33

Post by AdamH12113 »

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 topologies and chose the wrong one given the requirements.

* Generated utterly broken schematics for several simple circuits, with missing connections and aggressively-incorrect placement of decoupling capacitors.

Any one of these failures, individually, would break the entire design. The article's conclusion for this section buries the lede slightly:

> The AI generated circuit was three times the cost and size of the design created by that expert engineer at TI. It is also missing many of the necessary connections.

Cost and size are irrelevant if the design doesn't work. LLMs aren't a third as good as a human at this task, they just fail.

The LLMs do much better converting high-level requirements into (very) high-level source code. This make sense (it's fundamentally a language task), but also isn't very useful. Turning "I need an inverting amplifier with a gain of 20" into "amp = inverting_amplifier('amp1', gain=-20.0)" is pretty trivial.

The fact that LLMs apparently perform better if you literally offer them a cookie is, uh... something.

Re: Testing Generative AI for Circuit Board Design

#34

Post by stavros »

netsec_burn wrote: post #32
stavros wrote: post #16

Earlier quoted context omitted.

True, I just tried it for generating a book summary, and Sonnet 3.5 was very bad. GPT-4o is equally bad at that , gpt-4-turbo is great.

This more likely has to do with context length?

No, all the information is there, but gpt-4o tends to produce bullet points (https://www.thesummarist.net/summary/the-making-of-a-manager...), whereas gpt-4-turbo tends to produce much more readable prose (https://www.thesummarist.net/summary/supercommunicators/the-...).

Re: Testing Generative AI for Circuit Board Design

#35

Post by richie-guix »

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…

[flagged]

Re: Testing Generative AI for Circuit Board Design

#36

Post by hoosieree »

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 agree diffusion makes more sense for optimizing code-like things. The tricky part is coming up with a reasonable set of "add noise" transformations.

Re: Testing Generative AI for Circuit Board Design

#37

Post by lemonlime0x3C33 »

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…

thank you for summarizing the results, I feel much better about my job security. Now if AI could make a competent auto router for fine pitch BGA components that would be really nice :)

Re: Testing Generative AI for Circuit Board Design

#38

Post by LeifCarrotson »

cjk2 wrote: post #20
DHaldane wrote: post #18

Earlier quoted context omitted.

My gut agrees with you that LLMs shouldn't do this well on a specialty domain. 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. Overall not sure what to expect, but fine tuning experiments would be interesting regardless.

I doubt it'd work any better. Most of EE time I have spent is swearing at stuff that looked like it'd work on paper but didn't due to various nuances. I have my own library of nuances but how would you even fine tune anything to understand the black box abstraction of an IC to work out if a nuance applies or not between it and a load or what a transmission line or edge would look like between the IC and the load? Thi…

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 the equivalent of boilerplate code.

If I could tell an AI to generate a 100x100 prototype with such-and-such a microcontroller, this sensor and that sensor with those off-board connectors, with USB power, a regulator, a tag-connect header, a couple debug LEDs, and break out unused IO to a header...that would have huge value to my workflow, even if it gave up on anything analog or high-speed. Presumably you'd just take the first pass schematic/board file from the AI and begin work on anything with nuance.

If generative AI can do equivalent work for PCBs as it can do for text programming languages, people wouldn't use it for transmission line design. They'd use it for the equivalent of parsing some JSON or making a new class with some imports, fields, and method templates.

Re: Testing Generative AI for Circuit Board Design

#39

Post by jeffreygoesto »

cjk2 wrote: post #12
shrimp_emoji wrote: post #9

Earlier quoted context omitted.

It's like a generated image with an eye missing but for circuits. :D

AI proceeds to use 2n3904 as a thyristor. AI happy as it worked the first 10ns of the cycle.

Every natural Intelligence knows that you need to reach out to a 2N3055 for heavy duty. ;)

Re: Testing Generative AI for Circuit Board Design

#40

Post by neltnerb »

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 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 fixed every single error.

Post reply on HN