Rendered at 10:48:15 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
andyfilms1 12 hours ago [-]
Maybe I'm missing it, but I don't see how long it took to create these, or how much they cost (in tokens.)
PCB layout is a weird problem. As the article says, you can get halfway through before realizing you need to re-do everything, and there's no way to predict that from the outset. It's an inherently self-bottlenecked process.
There is also a lot of judgement that goes into it, that I'm not sure could ever be fully covered with AI. You can never hit 100% perfection on every metric (crosstalk, parasitics, DFM, BOM optimization, trace length matching, etc.) so determining where and by how much these things can fall short of optimal is very much a part of the process, and seems like it would be an overfitting nightmare for an AI.
There are also simply decisions that have no empirical right or wrong answer, but are still critical to the system functioning. What frequency do you want to run your data busses at? How much power can it draw? How long does it need to last in standby? How hot can it get?
10 hours ago [-]
jakescustomshop 11 hours ago [-]
There is a comparison plot that had model Electronics benchmark scores vs $ cost. All tested models were between $2000 and $5000.
I’ve been messing with GPT 6.1 sol PCB routing, but it always comes out really ugly and inefficient. It mostly just runs an autorouter.
Sol IS really good at part selection given loose parameters and JLCPCB’s inventory.
hard_times 11 hours ago [-]
We need a good modeling language for general purpose electronics, some sort of UML for hardware.
andyfilms1 10 hours ago [-]
I mean, that's what the schematic is for. But a logical diagram doesn't tell you the correct trace width and spacing for a particular impedance for a particular substrate, or the experience and context to know if that even matters for this project or not.
PCB layout is a weird problem. As the article says, you can get halfway through before realizing you need to re-do everything, and there's no way to predict that from the outset. It's an inherently self-bottlenecked process.
There is also a lot of judgement that goes into it, that I'm not sure could ever be fully covered with AI. You can never hit 100% perfection on every metric (crosstalk, parasitics, DFM, BOM optimization, trace length matching, etc.) so determining where and by how much these things can fall short of optimal is very much a part of the process, and seems like it would be an overfitting nightmare for an AI.
There are also simply decisions that have no empirical right or wrong answer, but are still critical to the system functioning. What frequency do you want to run your data busses at? How much power can it draw? How long does it need to last in standby? How hot can it get?
I’ve been messing with GPT 6.1 sol PCB routing, but it always comes out really ugly and inefficient. It mostly just runs an autorouter.
Sol IS really good at part selection given loose parameters and JLCPCB’s inventory.