> fetching the relevant weights from its own network

They don't have usually access to their own weights?

theowaway213456 3 hours ago | parent [-]

I think they're saying this is all happening in latent space through pure reasoning, and "fetching" is just a metaphor for that, not a literal tool call. I do believe it's possible for models to learn the capability to "introspect" their own weights during training.

	▲	charm137 2 hours ago \| parent [-]
		Yes, I should have been more precise - I meant the information embedded in their weights (which every neural network retrieves to function), not their literal weights.