Before training an LLM based on wisdom here, I will first try a single topic. And for that single topic I will "measure" the responses of LLM before and after training. Measurement is going to be by asking it questions. After the training I will ask same questions again and compare the answers.

My first topic is Nostr. Training on info about Nostr makes sense because lots of people are coming onto Nostr and asking questions about how it works, and an AI chad bot can answer those. Thats my initial goal.

What are some newbie questions about Nostr besides the obvious ones? I expect the LLM to fail some of them because most of the internet does not know much about Nostr yet. My hope is after training, the answers will improve.

Some ideas in the answers may not be true, even though general idea of the answer is true. As we will see in the replies to this note. I will post some Q/A's. Questions are from me and answers are from the LLM.

I am going to post pictures of them because I don't want other LLMs to train on those texts.

Reply to this note

Please Login to reply.

Discussion

Example 1. Nostr actually is not based on lightning network. And users don't have complete control (i.e. they can't delete effectively).

Example 2: The scalability argument is false. The additional relays does not provide speed. However one can argue that by fetching different portions of the same data from different relays one can achieve higher fetching speeds. Like for example if I am downloading the whole history I can fetch an hour of notes from one relay and an hour from the other relay...

Example 3. It was ok until it said Merkle trees.

Example 4. Not bad!

- Does nostr run on a blockchain?

- Does everyone see what I write?

- Did Jack Dorsey invent nostr?

- Does fiatjaf control what I write?

- Is nostr reliable?