Comment

Comment by MontyCarloHall

>The output of an LLM is produced by a superposition of simulated entities. When we give the LLM a prompt, it simulates every possible entity consistent with the prompt.

There is absolutely no theoretical justification for this assertion that LLMs somehow have some emergent quantum mechanical behavior, metaphorical or otherwise.

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton