alt Hacker Newsthat’s true of analyzing individual atoms in a combustion engine — yet I doubt you’d claim we don’t know how they work
also this went from “we can’t analyze” to “we can’t analyze reliably [without a lot of effort]” quite quickly
Replies
FeepingCreature • last Wednesday at 5:46 PM
I mean, fluid dynamics is an unsolved issue. But even so we know *considerably* less about how LLMs work in functional terms than about how combustion engines work.
➕ show 1 reply
In the digital world, we should be able to go back from output to input unless the intention of the function is to "not do that". Like hashing.
Llms not being able to go from output back to input deterministically and for us to understand why is very important, most of our issues with llms stem from this issue. Its why mechanistic interpretabilty research is so hot right now.
The car analogy is not good because models are digital components and a car is a real world thing. They are not comparable.