I think LLMs are going to be needed ultimately for algorithmic feed generation on Nostr, whether in a DVM form or another machinery. Haterz gonna hate but sometimes algos are useful.

The tool has to download everything from other relays for this to make sense. Doing something on relays is not a good idea, they have to be quick and dumb, like a switch for Nostr to work properly. LLM stuff should be done at another machine because it is intensive computation.

Some other LLM uses may be classification of NSFW or illegal stuff as write policy for relays; finding keywords for notes for searching the contents later; summary generation based on interests of a user, like a newspaper.

My current inspiration and efforts are around "truth in AI".

nostr:note1y0lkts6rmkf8vcs9p0j39m2wkr5slcmq97avwzp5s0w5zu3h3seqnwt8qj