GPT-2 was released in 2019. So at most, the best expert in LLMs has 5 years experience. Less if you think the LLM age didn’t start in earnest until GPT-3, 3.5, or 4. And each iteration brings changes in best practices for how to extract information from them.
Any expert in the field (not to mention anyone jumping in now) has to maintain an apprentice mindset. Things are moving fast, so keep learning, keep experimenting, and keep improving.