[nospice]

> 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 problem isn't that LLMs are bad at coding, it's that we're asking them to write new programs when they should be doing selection and integration".

[bee_rider]

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…

[klaff]

Copy/paste (from reference boards or examples in the datasheet) is pretty common when starting a new design but if you don't then figure out what each connection and external component are there for and adjust to your application (or sometimes figure out the part won't work for you) then you quite literally don't know what you are doing.

[senorrib]

That’s exactly how it has been working for me in code. I have a bunch of different components and patterns that the LLMs mix and match. Has been working wonderfully over the past few months.

[w0de0]

At what level of abstraction does programming become a process of selection and integration?

[shimman]

Why get philosophical and not just deal with the reality that 95% of the industry are dealing with languages that just compile down to C? We are already at some of the highest levels of abstraction thus far in the history of the trade.

[gopher_space]

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.

[johnfn]

Maybe you can provide some examples of what you would consider to be “novel” code?

The proof of the Erdos problem the other day was called novel by Terrence Tao. That seems novel to me.

[iwontberude]

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.

[belval]

Are most circuits novel? I'd assume that there is enough out there to fit 80% of PCB design needs and sure it can still be bad at the remaining 20%.

[estimator7292]

That's precisely how LLMs work for code, yes. Were you not aware?

[mikeayles]

Sorry, could have been more clear, LLM's are great at architecting high level design decisions, but terrible at the nitty gritty - without better tooling (with the right tooling, such as https://flux.ai, they are capable!).

I even had Gemini hallucinate a QFN version of the TPS2596 last night, it was so confident that the *RGER variant existed. In an automated pipeline, this would break things, but giving it a list of parts to use, it becomes a lot more useful!

[groundzeros2015]

That is exactly what LLMs are good at for code