“That’s not how these things work anymore! Yes, it is the underlying technology that pulls the whole apparatus together, and yes that part is opaque. But tool use — like the search grounding calls — is inspectable, and rather than trying to guess where in a training set of billions of documents the information came from, for that portion we can see a very small set of inputs into the answer, and make fairly sound inferences about what is going on”

That's what I have been saying all this time. It's not all about LLMs, it's also retrieval!

Honestly the librarians who are the most misleading and making the most noises are those who think they are “technical” because they can reference a certain paper that mentions briefly stochastic parrot!

It's embarrassing when librarians are supposedly good at search