LLMs are gap-fillers and will fill all gaps implicitly with the most average input.
- LLMs are gap-fillers and will fill all gaps implicitly with the most average input.
- So it's your job to give them non-average gaps to fill, to inject the entropy.
- If you ask it for a joke you will get one of ten hyper bland ones.
- If you ask it for a joke about the pope, an orange, and Richard Feynman, you'll get something novel.
- You'll get the most average answer to that very novel request, which will in turn be novel.