As someone who is not well versed in the current LLM paradigm, how are the LLMs for technical domains trained? I can imagine how a model based off interent text would make for a _general_ conversational partner, but I'm unsure how a model would produce accurate information from such a niche prompt.

Also curious: has anyone created an LLM for circuit schematics trained on HDL code?

Very cool application. It's nice to be reminded that people are actually trying to make useful products in a world where it seems everyone is trying to sell you a solution with no problem.