Something that strikes me, is that (the whole point of this thread is) if I want two LLMs to “have a conversation” or to work together as agents on similar problems we need to have same or similar context.
And to drag this back to politics - that kind of suggests that when we have political polarisation we just have context that are so different the LLM cannot arrive at similar conclusions
One of the most valuable techniques for building useful LLM systems right now is actually the opposite of that.
Context is limited in length and too much stuff in the context can lead to confusion and poor results - the solution to that is "sub-agents", where a coordinating LLM prepares a smaller context and task for another LLM and effectively treats it as a tool call.
Shared context is critical to working towards a common goal. It's as true in society when deciding policy, as it is in your vibe coded match-3 game for figuring out what tests need to be written.
And to drag this back to politics - that kind of suggests that when we have political polarisation we just have context that are so different the LLM cannot arrive at similar conclusions
I guess it is obvious but it is also interesting