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

31–40 of 106 posts

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

#31

Post by senorrib »

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…

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.

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

#32

Post by mikeayles »

jacquesm wrote: post #22
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 sounds very interesting, especially if you combine it for instance with an FPGA for logic blocks.

Thanks, as a concept it has potential, I've leveraged some of my previous projects www.circuitsnips.com for inspiration for the subcircuit blocks, TOKN for more accurate parsing of schematics, and to a lesser extent even my datasheet MCP server and kicad-netlist tool, more info at https://www.mikeayles.com/

For the time being, I'm erring away from feature creep, even though I really, really want to though! For the sorts of products I would like this to make for the time being, simple I2C, SPI and GPIO driven peripherals are the limit. I only have 2 more weeks, and then I want to have a working, battery powered device on my desk. PCB, Enclosure, Firmware, everything.

Similarly, I haven't got a framework for anything mechatronic in the MCAD pipeline, so no moving parts (besides clickable buttons). Fixed devices are fine, like screens and connectors though.

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

#34

Post by jacquesm »

mikeayles wrote: post #32
jacquesm wrote: post #22

Earlier quoted context omitted.

This sounds very interesting, especially if you combine it for instance with an FPGA for logic blocks.

Thanks, as a concept it has potential, I've leveraged some of my previous projects www.circuitsnips.com for inspiration for the subcircuit blocks, TOKN for more accurate parsing of schematics, and to a lesser extent even my datasheet MCP server and kicad-netlist tool, more info at https://www.mikeayles.com/ For the time being, I'm erring away from feature creep, even though I really, really want to though! For the so…

Is there a way to stay up to date with what you are doing?

It very much aligns with how I've approached hardware since I was 15 and had a massive stack of functional blocks of electronics circuitry that I would combine in all kinds of ways. I've lost the 3x5's, but I still work that way, build a simple block, test it, build another block, test that, hook the one to the other etc.

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

#35

Post by mikeayles »

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…

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!

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

#36

Post by stuartaxelowen »

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’m curious why you don’t target an HDL, which seems like it should match very well to llm capabilities, and rely on existing layout solvers for describing the last physical layout step?

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

#37

Post by mikeayles »

jacquesm wrote: post #34
mikeayles wrote: post #32

Earlier quoted context omitted.

Thanks, as a concept it has potential, I've leveraged some of my previous projects www.circuitsnips.com for inspiration for the subcircuit blocks, TOKN for more accurate parsing of schematics, and to a lesser extent even my datasheet MCP server and kicad-netlist tool, more info at https://www.mikeayles.com/ For the time being, I'm erring away from feature creep, even though I really, really want to though! For the so…

Is there a way to stay up to date with what you are doing? It very much aligns with how I've approached hardware since I was 15 and had a massive stack of functional blocks of electronics circuitry that I would combine in all kinds of ways. I've lost the 3x5's, but I still work that way, build a simple block, test it, build another block, test that, hook the one to the other etc.

Feel free to star/watch the repo for the project at: https://github.com/MichaelAyles/heph

I may be able to set up an RSS feed for the blog if that interests you? edit: https://phaestus.app/feed.xml

There's a limited sign up currently on the site, which currently goes to an approval page. I don't think I'm quite ready for it to be fully open yet, as i'm paying all the inference, but I should be starting to populate the gallery soon with generated projects.

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

#38

Post by groundzeros2015 »

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…

That is exactly what LLMs are good at for code

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

#39

Post by y1n0 »

stuartaxelowen wrote: post #36
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’m curious why you don’t target an HDL, which seems like it should match very well to llm capabilities, and rely on existing layout solvers for describing the last physical layout step?

This seems to be a discussion about board level circuits. HDLs are for chip design.

So far the language models aren’t great at HDL but I assume it’s just a training priority thing and not some characteristic of HDLs.

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

#40

Post by walterbell »

mikeayles wrote: post #37
jacquesm wrote: post #34

Earlier quoted context omitted.

Is there a way to stay up to date with what you are doing? It very much aligns with how I've approached hardware since I was 15 and had a massive stack of functional blocks of electronics circuitry that I would combine in all kinds of ways. I've lost the 3x5's, but I still work that way, build a simple block, test it, build another block, test that, hook the one to the other etc.

Feel free to star/watch the repo for the project at: https://github.com/MichaelAyles/heph I may be able to set up an RSS feed for the blog if that interests you? edit: https://phaestus.app/feed.xml There's a limited sign up currently on the site, which currently goes to an approval page. I don't think I'm quite ready for it to be fully open yet, as i'm paying all the inference, but I should be starting to populate th…

RSS feed would be helpful.
Post reply on HN