This is very interesting indeed. I need to keep wrapping my head around this, but I have a doubt. How large does the initial prompt have to be? AFAIK, this initial prompt that both users need to use in order to initialize the LLM state so they can decode would work as a kind of “symmetric key,” right? If this is true, I was just wondering how secure or what is the shape of that initial prompt is, and whether it is susceptible to brute forcing in some way. Because for someone to participate in a conversation, they just need the LLM model and the prompt, and then they can exchange encoded messages out of band, right? Please correct me if I’m wrong on any of the points; I’m still trying to understand this :)

Thanks for sharing this 🧡

Well that's cordn sir

Trading resilience for performance, is a good tradeof depending on the case.
I will check the spec so maybe we can come with a more interoperable standard that doesn't depend on an specific transport

Bad idea, imho. Not as bad as NIP-04, but getting closer. Also, it will make nip 17 DM traffic distinguishable from all other gift wrap traffic, which, from my point of view, really harms metadata protection. Currently, I don’t consider nip 17 private, but this would make it much worse. Have you read my article on this subject?

That could be because gift wraps are used for purposes other than DMs. They’re considered a very spammy kind, yet they also obfuscate traffic well. Have you read my article about private comms over public infra?

It doesn't work like that😅

Poetry

https://njump.me/nevent1qqsvy5gaeftshz9kskduyvjhpunmhpstfcg55wlg69at85kh29v3rysppamhxue69uhkummnw3ezumt0d5pzqs9eep0ll6hurjkl3sc2fewgses07mjfwxsdcu3at2m8fd0xrdz3klfjms

nostr: