-
We are prototyping a mechanism for group discussions.
- Through interactions with individual AI, 100 million people can indirectly engage in discussions.
- In this scenario, it becomes crucial to determine how to share discussion content among AIs.
- We are considering that by treating the entirety of “discussion content” as a set of pairs like “if this argument is made, then this argument is returned,” synchronization of discussion content can be achieved.
- Synchronization Step 1: Arguments made by User A are saved in a shared database.
- From the discussions between User A and AI, pairs like “User A responds with this argument to AI’s argument” are extracted and stored in the database.
- For example, from the left discussion, pairs like “If AI argues this, User A responds with this” are extracted and stored in the database as shown in the right figure.
- The figure plots similar arguments close to each other.
- The data from Public Opinion Map could be useful for this plotting.
- For instance, pairs of arguments like “Selective separate surnames may undermine the sense of family unity -> Families that break unity over just a name never had unity to begin with” are saved in the database.
- The figure plots similar arguments close to each other.
- Synchronization Step 2: AI conversing with User B refers to the shared database to respond, and User A’s argument reaches User B.
- When generating a response, the AI searches the shared database through vector search based on User B’s statement.
- It finds pairs of arguments like “Selective separate surnames may undermine the sense of family unity -> Families that break unity over just a name never had unity to begin with” and uses this reference to generate a response.
- Through interactions with individual AI, 100 million people can indirectly engage in discussions.
-
User’s Joy
- Users can asynchronously and indirectly collide with the opinions of real others.
- Immediate feedback such as counterarguments or agreements to one’s opinions expands social perspectives and serves as a means to understand the viewpoints of others.
- (Is there a need for this..?)
- It seems to depend on the context.
- For example, if discussions heat up in a way similar to Not eliminating the division of the world, but creating 100 divisions of the world, then it could be plausible.
- It depends on how it is mixed (elementary).
- It seems to be generally leaning towards conflict avoidance, so it may not be something that many people would prefer.
- On the other hand, a minority might like it.
- It seems to depend on the context.
- The idea of “your opinion reaching someone” and “your voice being heard in a space where many people discuss” is valuable.
- It would be beneficial if the results also reach politicians and decision-makers.
- Users can asynchronously and indirectly collide with the opinions of real others.
-
Joy of Broad Listening
- If we consider “almost identical arguments” in this data as the same node, a graph representing the “totality of discussions” can be created.
- Analyzing this graph seems to offer various interesting insights.
- For example, it could reveal tendencies where discussions tend to converge on certain nodes.
- Nodes that are frequently referenced are likely to represent crucial points of discussion.
- And so on.
- Loops might occur, leading to a sense of “oh no” haha (nishio).
- Recognizing loops could help identify fruitless arguments, enabling progress to the next stage.
- I vaguely remember writing about this with a diagram and explanation, but since it’s not particularly important, I’ll leave it be.
-
Food for Thought
- Things I was contemplating in selfsynth and Lab Use 20240801.
-
Thoughts
- The data structure of the shared database in medium-chat is crucial.
- Personal information is not very relevant.
- It is sufficient to record the premises associated with human-made arguments.- Accumulate “claims” that arise during discussions as a graph.
- Personal information is not very relevant.
- Aggregate similar claims using LLM or sentence embedding.
- Conceptually, it forms a chain of graphs with a syllogistic structure: “major premise,” “minor premise” → “conclusion.”
- It is possible to arrive at the same conclusion from different premises.
- The data structure of the shared database in medium-chat is crucial.
-
Each node is also an embedded vector, so the graph is visualized on a vector space.
- If there are connections like A->B and C->D, and A is very similar to C, and B is very similar to D, they should merge.
- Adjusting weights or other methods can be used.
- Representing “arguments” as a “weighted graph on a vector space.”
- If there are connections like A->B and C->D, and A is very similar to C, and B is very similar to D, they should merge.
-
When someone responds with “indeed,” it indicates agreement.
- Continuously doing this will gradually lead to finding “convincing arguments” that persuade many people.
- Individuals can then follow a graph path to reach that argument.
- Continuously doing this will gradually lead to finding “convincing arguments” that persuade many people.
-
Mechanism of conversation
- The concept of a “consistent personality of claims” seems helpful for humans to organize the current situation.
-
Implementation Proposal
- Extract many pairs of “claim (AI)” → “response (human)” from logs of discussions between humans and AI.