> "Even if all the model is capable of is memorizing text then just the sheer volume it has memorized should yield unique insights, no human can ever hope to hold this much text in their memory and then make connections between it."
Yes, potentially, but the model has no curiosity or drive to do this (or anything else) by itself. All an LLM is built to do is predict. The only way to control the output and goad it into using the vast amount of knowledge that it has is by highly specific prompting.
Basically it's only going to connect the dots if you tell what dots to connect, in which case it's the human being inventive, not the model. The model is trying to predict, so essentially if you want it to do something outside of the training set you're going to have to prompt it to do that.
A human has curiosity (e.g. "what happens if I connect these dots .."), based on prediction failure and associated focus/etc - the innate desire to explore the unknown and therefore potentially learn. The model has none of that - it can't learn and has no curiosity. If the model's predictions are bad it will just hallucinate and generate garbage, perhaps "backtrack" and try again, and likely lead to context rot.
Yes, potentially, but the model has no curiosity or drive to do this (or anything else) by itself. All an LLM is built to do is predict. The only way to control the output and goad it into using the vast amount of knowledge that it has is by highly specific prompting.
Basically it's only going to connect the dots if you tell what dots to connect, in which case it's the human being inventive, not the model. The model is trying to predict, so essentially if you want it to do something outside of the training set you're going to have to prompt it to do that.
A human has curiosity (e.g. "what happens if I connect these dots .."), based on prediction failure and associated focus/etc - the innate desire to explore the unknown and therefore potentially learn. The model has none of that - it can't learn and has no curiosity. If the model's predictions are bad it will just hallucinate and generate garbage, perhaps "backtrack" and try again, and likely lead to context rot.