Hacker News new | ask | show | jobs
by AdamH12113 724 days ago
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.

4 comments

Yes, this seemed pretty striking to me: the author clearly wanted the LLM to perform well. They started with a problem for which solutions are pretty much readily available on the internet, and then provided a pretty favorable take on the model's mistakes.

But the bottom line is that it's a task that a novice could have solved with a Google search or two, and the LLM fumbled it in ways that'd be difficult for a non-expert to spot and rectify. LLMs are generally pretty good at information retrieval, so it's quite disappointing.

The cookie thing... well, they learn statistical patterns. People on the internet often try harder if there is a quid-pro-quo, so the LLMs copy that, and it slips past RLHF because "performs as well with or without a cookie" is probably not one of the things they optimize for.

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.

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.

Hah, you're not kidding. Literally my comment was inspired by a recent realization that it is not possible to search for a RF connector by footprint size.

That's absurd to me, it took so long to figure out which random sequence of letters was the smallest in overall PCB footprint.

Maybe we found it, we think it's the AYU2T-1B-GA-GA-ETY(HF) but sure would be nice if Digikey had a search by footprint dimensions.

Yet strangely the physical ability of a device to fit into a location you need it is not in the list of things I can search. Takes ten seconds to find the numbers -- after I download and open the PDF file.

https://www.digikey.com/en/products/filter/coaxial-connector...

Just so strange, but so common. And digikey is heads and shoulders above average, McMaster might be the only better one I know of at it and they're very curated.

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.
Anyone looking for an idea for something potentially valuable to make: ingest PDF datasheets and let us search/compare etc, across them. The PDF datasheet is possibly one of the biggest and most unecessary hurdles to electronics design efficiency.
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
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 :)