[westoncb]

I think this is an important perspective. It helps clarify prompting as well because, used in a certain way, they are effectively natural language specification of constraints which have the effect of 'partially configuring' the network so that its inference selects from the configuration space of its still free params

For example, if you tell it to reply in JSON (and it obeys), you've just constrained its search space in a particular way. There is space for very interesting informal programming that can be done from this perspective, setting up constraints and then allowing inference to solve within them. I've been using this heavily.

When I was first getting deep into LLM stuff a few months ago and contemplating latent space my main characterization was that much of its high level behavior can be usefully grappled with by viewing it as a kind of 'learned geometric prolog'.

I did a bunch of illustrations and talked about some of these ideas here if anyone's curious: https://x.com/Westoncb/status/1757910205478703277 (I think I mostly dropped the prolog terminology in that presentation because not everyone knows about it)