Hacker News Reader

In our company, we are doing high speed PCB designs with FPGAs, memories, ADCs, DACs etc. We are not yet using AI much in our PCB design workflow because our designs seem to be too complex for the AI solutions we have tried. Are there any areas where people are successfully incorporating AI to their PCB design workflow, even with complex, high speed designs? Schematic/layout review? Routing? Footprint creation?

View on HN

Why wouldn't an LLM be able to do high speed designs? Are you inventing new types of design rules for every board? Or is it simply because the automatic layout tools are not up to the task yet?

It is just that the current tools out there seem to work for small or hobbyist boards currently. We couldn't apply them on our complex board designs. But maybe you had a different experience? I am curious on what kind of ways big companies are incorporating AI in their PCB design workflows currently.

The feedback loop is too long, it's not like a software development harness that can direct the model to write some tests for complex behavior, and iterate until they pass.

There a lots of things that can be subtly wrong, and it gets much worse as your signal frequency increases, or you have to deal with high power/radio/etc. The model (agent) has no way to validate its work.

Reply on news.ycombinator.com