https://adjacentpossible.substack.com/p/project-tailwind

On the Tailwind team we’ve been referring to our general approach as source-grounded AI. Language models, as we all know, have a habit of hallucinating facts, and while the information contained in the model’s training data is vast, it is also one-size-fits-all. Tailwind allows you to define a set of documents as trusted sources which the AI then uses as a kind of ground truth, shaping all of the model’s interactions with you. In the use case shown on the I/O stage, the sources are class notes, but it could be other types of sources as well, such as your research materials for a book or blog post. The idea here is to craft a role for the LLM that is not an all-knowing oracle or your new virtual buddy, but something closer to an efficient research assistant, helping you explore the information that matters most to you.

Figuring out what to mark as a "trusted source" might be tricky, depending on the application, but having an instantly searchable "notebook" of sorts that can give sensible, customized, personal answers in a quick English prompt would be very useful.

It reminds me of the stuff that (IIRC) used to be called "expert systems". I wonder how it's different (other than having some Chat thing layered on top).

(via DeLong's Briefly Noted thing for today. You know that "efficient research assistant" was music to his ears.)

Cheers,
Scott.