marcano on Nostr: I think it would be better if each rabbit hole were silo'd to only the context ...
I think it would be better if each rabbit hole were silo'd to only the context upstream.
For instance, I might ask "what is nostr" and an LLM may tell me its a cryptographic, interoperable social media protocol.
Which I might need clarification on cryptography before continuing the discussion on interoperable social media protocol. (cryptography is how it works, not what it is)
I clarify my understanding of cryptography in thread 2, but thread 1 is more along the lines of things that are newly possible with interoperable social protocols.
The LLM doesn't need to process our cryptography conversation (and all the tokens associated with it) to converse about social media.
For instance, I might ask "what is nostr" and an LLM may tell me its a cryptographic, interoperable social media protocol.
Which I might need clarification on cryptography before continuing the discussion on interoperable social media protocol. (cryptography is how it works, not what it is)
I clarify my understanding of cryptography in thread 2, but thread 1 is more along the lines of things that are newly possible with interoperable social protocols.
The LLM doesn't need to process our cryptography conversation (and all the tokens associated with it) to converse about social media.