←back to thread

Why language models hallucinate

(openai.com)
277 points simianwords | 2 comments | 06 Sep 25 07:41 UTC | HN request time: 0s | source
Show context
manveerc ◴[06 Sep 25 20:16 UTC] No.45152495[source]▶
Maybe I am oversimplifying it, but isn’t the reason that they are lossy map of worlds knowledge and this map will never be fully accurate unless it is the same size as the knowledge base.

The ability to learn patterns and generalize from them adds to this problem, because people then start using it for usecases it will never be able to solve 100% accurately (because of the lossy map nature).

replies(1): >>45152567 #
1. Peritract ◴[06 Sep 25 20:25 UTC] No.45152567[source]▶
As with a lot of AI stuff, Borges already wrote about it.

https://www.sccs.swarthmore.edu/users/08/bblonder/phys120/do...

replies(1): >>45152713 #
2. manveerc ◴[06 Sep 25 20:47 UTC] No.45152713[source]▶
That’s more elegantly put than I ever can.

Btw I am not disagreeing with the utility of LLMs, my point is it can never be 100% accurate with current architecture (unless you blow up the size).