[stn8188]

Definitely not GPT-style, but there are quite a few examples of ML/AI integration with EDA. For example:

Startup looking at a post-layout DFM check workflow: https://cadstrom.io/

Cadence is probably the biggest EDA company talking about ML/AI in the PCB space (that I've noticed) with their recently announced "Allegro X" stuff. The videos are mostly marketing fluff, but they seem to be on track with what I'd expect for "AI assisted PCB design". https://www.cadence.com/en_US/home/tools/pcb-design-and-anal... https://www.youtube.com/watch?v=RlWfSQq0NkA

They also have a neat machine-learning optimization tool for their electronics simulations: https://www.cadence.com/en_US/home/tools/system-analysis/opt...

On the chip-design side of EDA, both Cadence and Synopsys have a bunch of AI-assisted tools that supposedly are being used right now. I'm not as familiar with that stuff so I prefer to read the humorous Deep Chip summaries: http://www.deepchip.com/items/0593-08.html

And lastly, there's some recently published and soon-to-be-published work showing that there's potential to speed up electromagnetic simulations with neural nets. It's all just proof-of-concept for now, but I'm hoping this proves that ML/AI can be can be integrated in a useful manner in commercial electromagnetic solvers :) https://shielddigitaldesign.com/posts/2022/ml-replace-field-... https://shielddigitaldesign.com/posts/2023/s-param-from-via/