News for hackers. Stuff that matters.

A comment on Language models can explain neurons in language models. Parent comment

Re:Language models can explain neurons in language models by creatonez on Wednesday May 10, 2023 @01:59AM (#35884136)
It's not clear whether or not LLMs have internal thoughts -- each token generation could absolutely have a ton of thought-like modelling in the hidden layers of the network.

What is known is that these internal thoughts get erased each time a new token is generated. That is, it's starting from scratch from the contents of the text each time it generates a word. But you could postulate that similar prompt text leads to similar "thoughts" and/or navigation of the concept web, and therefore the thoughts are continuous in a sense.

[ Parent | on HN ]
Re:Language models can explain neurons in language models by callesgg on Wednesday May 10, 2023 @02:42AM (#35884384)
True, LLMs definetly has something that is "thought-like".

But todays networks lacks the recursion(feedback where the output can go directly to the input) that is needed for the type of internalized thoughts that humans have. I guess this is one thing you are pointing at by mentioning the continuousnes of the internals of LLMs.

[ Parent | on HN ]