YODL on Nostr: Ok, finished reading it. It’s really good and fleshed out! A lot of the framing you ...
Ok, finished reading it. It’s really good and fleshed out! A lot of the framing you gave clarified some vague concepts I held but never considered very carefully. Definitely shifted my schema about knowledge databases a bit.
I gathered you spend a lot of time with graphs and ML. Was curious what you do exactly for say connecting notes with some sematic-weighted distance measure. I know a bit about this, so no need to dumb it down too much if you choose to elaborate. My guess is you leverage some state of the art LLM model and then build a “simple” ML model with some popular distance choice to rank things relative to one another.
I gathered you spend a lot of time with graphs and ML. Was curious what you do exactly for say connecting notes with some sematic-weighted distance measure. I know a bit about this, so no need to dumb it down too much if you choose to elaborate. My guess is you leverage some state of the art LLM model and then build a “simple” ML model with some popular distance choice to rank things relative to one another.