LLMs are gap fillers.

  • LLMs are gap fillers.
    • They fill in the gaps you left with the average answer.
    • They give you the most plausible next token.
      • The most average.
      • They reveal a certain tendency of the universe, in tune with something deep and hidden.
    • If the average is right, you don't need to specify.
      • You only need to specify the novel parts.
      • Way less encoding, you can rely on the rest of the world's knowledge implicitly.