I would also suggest spending a few minutes to set up an mCP server with ghidra once you've learned the basics of navigating and working inside of ghidra.
Turns out that frontier grade llms are absolutely fantastic for extremely advanced static analysis. If you go one step further and manage to get your firmware running inside of an emulator or other place where you can attach GDB... Then putting an mCP server on that as well unlocks so much insane potential.
Would that include free use LLMs. I assume getting into something would be tricky if you are assuming they're going to drop several hundreds of tokens a month on it.
I feel like the tendency for people to assume others have nearly $500 or so of credits on their AI to blow every month is kinda crazy.
Reminds me of the "just get Netflix, Prime, etc." ending up with a $100/m bill.