-
Things to consider:
- Ideas pondered in selfsynth and Lab Use 20240801.
-
Considerations:
- The data structure of a shared database in [medium-chat] is crucial.
- Personal information is not that relevant.
- It is sufficient to record the premises associated with a person’s assertions.
- Personal information is not that relevant.
- Accumulating “assertions” that arise during discussions as a graph.
- Using LLM and sentence embedding to aggregate similar assertions.
- Imagining a chain of graphs following a syllogistic structure: “major premise,” “minor premise” → “conclusion.”
- It is entirely possible to arrive at the same conclusion from different premises.
- Each node is also an embedded vector, so the graph exists on a vector space.
- If A->B and C->D, and A is very similar to C and B is very similar to D, they should merge.
- Adjusting weights, for example.
- Expressing “discussions” as a “weighted graph on a vector space.”
- If A->B and C->D, and A is very similar to C and B is very similar to D, they should merge.
- If someone agrees with a response, they should express it.
- Continuously doing this should lead to gradually finding “convincing arguments” that persuade many people.
- Individuals can then follow paths through the graph to reach those arguments.
- Continuously doing this should lead to gradually finding “convincing arguments” that persuade many people.
- Mechanism of conversation:
- The concept of a “consistent personality of assertions” seems useful for humans to organize the current situation.
- The data structure of a shared database in [medium-chat] is crucial.
-
Implementation proposal:
- Extract many pairs of “assertion (AI)” → “response (human)” from logs of discussions between humans and AI.