Just chilling and sharing a stream of thought…
So how would a credibility system work and be implemented. What I envision is something similar to the up votes…
You have a credibility score, it starts a 0 neutral. You post something People don’t vote on if they like, the votes are for “good faith”
Good faith is You posted according to rules and started a discussion You argued in good faith and can separate with opposing opinions You clarified a topic for someone If someone has a polar opinion to yours and is being down voted because people don’t understand the system Etc.
It is tied to the user not the post
Good, bad, indifferent…?
Perfect the system
I have an idea. Have every single article or comment posted by a user scanned by an LLM. Prompt the LLM to identify logical fallacies in the post or comment. Post the user logical fallacies counts on a public scoreboard hosted on each federated instance. Now, ban the top 10% scoring users each quarter who have a fallacy ratio surpassing some reasonable good faith objective.
Pros: Everyone is judged by the same impassive standard.
Cons: 1) A fucking LLM has to burn coal for every stupid post we make. 2) LLM prompt injection/hijacking vulnerability.