A number of ranking techniques used to require huge numbers of users to be effective.
If you had millions of users, and there was a consistent asymmetry in user behavior, however small, at large enough scale the noise would cancel out and the signal would be left.
Almost every human using the system does a tiny bit of work, without realizing it.
Distilling all of that micro-work can produce a strong signal.
But this required millions, or hundreds of millions of users.
But now you can do this with LLMs at orders of magnitude smaller scales.
Instead of having to distill signals from data exhaust (since the human can't be asked to do anything more than a micro amount of implicit work), you can ask the LLM to think deeply about it.
The LLM will happily do the work, it might just take a few seconds.
But if you do it after the user's query, then you can be ready to have improved quality quickly for the next time.