@ton using a personalized LLM as a research assistant 🤔… when seeing the Google I/O announcement, immediately thought about Dovetail. But, this snippet you share here makes me realize that though didn’t go far enough. Might need to (reluctantly) investigate this some more write ✍🏽 🗒️
@Avancee I'd be very interested in having a way to feed my 25+ yrs of notes and writings in a localised LLM assistant. If only I could keep my data out of the hands of tech companies and their clouds and models.
@ton I think there’s a path for figuring that out with many of the LLM models/remixes out here now. Wrapping that into something which could stand the test of (software and hardware) time will be a thing to figure out. But, a personal repo, with a data model/transformer that only works on that local data store… yea that would be aces