New things will still be documented, which LLMs can digest. The documentation may have been auto-generated by a different LLM, no problem.
Incorporating recent info into an LLM (fine tuning) is a solved problem.
Incorporating recent info into an LLM (fine tuning) is a solved problem.
Unfortunately, I can't think of a real-world example (library where ChatGPT has probably seen the documentation, but not any source code) to try out.