One use of LLMs that I haven’t seen mentioned before is to use them as a sounding board for your own ideas. By discussing your concept with an LLM, you can gain fresh perspectives through its generated responses.
In this context, the LLM’s actual comprehension is irrelevant. The purpose lies in its ability to spark new thought processes by prompting you with unexpected framings or questions.
Definitely recommend trying this trick next time you’re writing something.
I did this with ChatGPT once and can’t say I had a good time . To be fair , what I was pitching to it was to unusual yet similar for it to grasp it .
So yeah as long as the LLM doesn’t get to overconfident with thinking it knows what you’re talking about , you might be able to get somewhere .
Yeah it definitely works for some topics better than others. Also depends a lot on the model and what it was trained on.