alt Hacker News> 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".
Replies
At what level of abstraction does programming become a process of selection and integration?
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.
That's precisely how LLMs work for code, yes. Were you not aware?
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.
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!
That is exactly what LLMs are good at for code
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…