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

"Anyone else out there vibe circuit-building?"

twitter.com

Post reply on HN
Print view View original

61–70 of 106 posts

Re: "Anyone else out there vibe circuit-building?"

#61

Post by bee_rider »

nospice wrote: post #25
mikeayles wrote: post #11

Been working on this exact problem for a while now. The core issue isn't that LLMs are bad at circuits, it's that we're asking them to do novel design when they should be doing selection and integration. My project ( https://phaestus.app/blog ) takes a different approach: pre-validated circuit blocks on a fixed 12.7mm grid with standardized bus structures. The LLM picks which blocks you need and where they go, but th…

> The core issue isn't that LLMs are bad at circuits, it's that we're asking them to do novel design when they should be doing selection and integration. I don't want to detract from what you're building, but I'm puzzled by this sentence. It very much sounds like the problem is that they're bad at circuits and that you're working around this problem by making them choose from a catalog. Try that for code. "The proble…

I only had undergrad EE training so maybe I’m out of touch with what’s done in industry. But, I think most human engineers mostly don’t design novel circuits either. Chips come with specification sheets that have some reference implementations. So obviously somebody at the company designs that reference implementation, but I think most users stick pretty close to it…

Re: "Anyone else out there vibe circuit-building?"

#62

Post by iwontberude »

gopher_space wrote: post #47
nospice wrote: post #25

Earlier quoted context omitted.

> The core issue isn't that LLMs are bad at circuits, it's that we're asking them to do novel design when they should be doing selection and integration. I don't want to detract from what you're building, but I'm puzzled by this sentence. It very much sounds like the problem is that they're bad at circuits and that you're working around this problem by making them choose from a catalog. Try that for code. "The proble…

Are there examples of LLMs generating novel code? If so, who is it novel to? Not trying to be a smart ass here, I’ve been keeping an eye out for years.

Everything is derivative of something else. “Novel” is a distinction for works which are minimally derived, but everything created is a remix of something else. Novelty is an illusion.

Re: "Anyone else out there vibe circuit-building?"

#63

Post by elictronic »

jacquesm wrote: post #57
JKCalhoun wrote: post #46

Earlier quoted context omitted.

The breadboard has validated the communication between the ESP32 and ADC chip (over I2C). It's enough that I've now moved to KiCad layout and will wait for the boards to come back to see if the actual ADC data I am getting is more or less linear, noiseless…

Ah ok! Thanks for that bit of clarification, it makes a world of a difference, yes, you can use the breadboard for that, but - based on my own experience - if you want to actually use an ADC on a breadboard you're going to be in for a world of hurt as soon as you exceed some very low threshold frequency of updating and you're going to be fighting all kinds of weird bias effects. The parasitic capacitance of those bre…

Large metal planes uniformly spaced. At what point is the parasitic capacitance just a capacitor.

Re: "Anyone else out there vibe circuit-building?"

#64

Post by UncleEntity »

st_goliath wrote: post #33

> Thought for 37s > ... > Ah - that makes sense, that's why it's on fire oh how very relatable, I've had similar moments. I knew about SEDs (smoke emitting diodes) and LERs (light emitting resistors), but what do you call the inductor version?

Would that be Rapidly Decompressing Capacitors?

...only know what an inductor is from watching a video one the youtubes where they were talking about using them on the suspensions of F1 cars and they explained their relationship to electronic circuits, forget what their actual name is.

Re: "Anyone else out there vibe circuit-building?"

#65

Post by marcosdumay »

JKCalhoun wrote: post #43
nospice wrote: post #15

Earlier quoted context omitted.

Both Gemini and ChatGPT have a pretty comically wrong knowledge of op-amps. They usually recommend outdated chips and are confused about circuit topologies. I was looking at this last week and it hasn't changed. I asked them to suggest and evaluate microphone circuits and they were just bad. I would really, really recommend reading some human-written text if you're learning about that. I can't think of any reason why…

Thanks, I have read a lot of human-written text (and actual books from the day) in addition to the LLM feedback. Again though, had I ignored LLMs altogether I would have barely progressed in the past two months. I think. They seem to act as an "idea board" of sorts—sends me out then looking for others to validate (or not) what they're spouting. "Schottky diodes to protect op-amp inputs…" Not op-amp inputs, ADC inputs…

Those ADC probably also have protection diodes, take a look at the datasheet because you may be better with other options, and very likely can use diodes with a larger band gap if you really need bulky protection.

Re: "Anyone else out there vibe circuit-building?"

#66

Post by Palomides »

PunchyHamster wrote: post #52
mikeayles wrote: post #11

Been working on this exact problem for a while now. The core issue isn't that LLMs are bad at circuits, it's that we're asking them to do novel design when they should be doing selection and integration. My project ( https://phaestus.app/blog ) takes a different approach: pre-validated circuit blocks on a fixed 12.7mm grid with standardized bus structures. The LLM picks which blocks you need and where they go, but th…

I think Altium tried to do something similar. A bunch of common blocks being able to just plop on the PCB, (auto) route few tracks and done. Failed because there was always something some client wanted to do, move, change or optimize for production run. Module based design is cool for getting the prototype going but once you get into production you want to optimize everything so it falls apart quickly when you need t…

I think it's also that hardware costs are so easy to quantify compared to engineering labor and software dependency maintenance etc

Re: "Anyone else out there vibe circuit-building?"

#67

Post by invokestatic »

mikeayles wrote: post #11

Been working on this exact problem for a while now. The core issue isn't that LLMs are bad at circuits, it's that we're asking them to do novel design when they should be doing selection and integration. My project ( https://phaestus.app/blog ) takes a different approach: pre-validated circuit blocks on a fixed 12.7mm grid with standardized bus structures. The LLM picks which blocks you need and where they go, but th…

This is conceptually interesting to me because I see this as almost a more generic TI Webench. I’m curious why your focus in the sized “grid” blocks (presumably for placement directly on the PCB layout) instead of doing the same but for the schematic. That way I still have the flexibility of laying out the board how I want to meet eg mechanical constraints instead of working around a 12.7mm grid.

Re: "Anyone else out there vibe circuit-building?"

#68

Post by jacquesm »

elictronic wrote: post #63
jacquesm wrote: post #57

Earlier quoted context omitted.

Ah ok! Thanks for that bit of clarification, it makes a world of a difference, yes, you can use the breadboard for that, but - based on my own experience - if you want to actually use an ADC on a breadboard you're going to be in for a world of hurt as soon as you exceed some very low threshold frequency of updating and you're going to be fighting all kinds of weird bias effects. The parasitic capacitance of those bre…

Large metal planes uniformly spaced. At what point is the parasitic capacitance just a capacitor.

And an antenna, and a coil. Breadboards are great for slow and digital up a few 100 Khz, above that you are going to have the occasional interesting challenge / hairpulling session.

Re: "Anyone else out there vibe circuit-building?"

#69

Post by mikeayles »

invokestatic wrote: post #67
mikeayles wrote: post #11

Been working on this exact problem for a while now. The core issue isn't that LLMs are bad at circuits, it's that we're asking them to do novel design when they should be doing selection and integration. My project ( https://phaestus.app/blog ) takes a different approach: pre-validated circuit blocks on a fixed 12.7mm grid with standardized bus structures. The LLM picks which blocks you need and where they go, but th…

This is conceptually interesting to me because I see this as almost a more generic TI Webench. I’m curious why your focus in the sized “grid” blocks (presumably for placement directly on the PCB layout) instead of doing the same but for the schematic. That way I still have the flexibility of laying out the board how I want to meet eg mechanical constraints instead of working around a 12.7mm grid.

I saw routing as equally as big of a headache as the schematic, so formalizing the layout to a grid means layout becomes a compilation problem, not a design problem.

My intent for phaestus isn't to design pcb's, it's to design entire products, and also to be friendly to non technical users who don't know what a PCB is, let alone do layout themselves.

Re: "Anyone else out there vibe circuit-building?"

#70

Post by K0balt »

If you have solid domain knowledge, LLMs are a force multiplier for electronic design. You just have to have a spider sense for “this is going off the rails”.

Other than that, it does useful circuit review, part selection (or suggestions for alternative parts you didn’t know existed), and is usually usefully skeptical. It’s also great at quick back of the napkin “can I just use a smt ceramic here?” Type calculations, especially handy for roughing out timings and that kind of thing.

Post reply on HN