probabilities and values

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by

In the race ending, Agent-4 has partial alignment with humanities’ goals which then persist into Agent-5, Consensus-1, and any surviving models thereafter. 

I’ll present an idea for a course of action at the Agent-4 branching point.

We have partial alignment to work with. We can negotiate beforehand to reach a settlement with these future models. We can negotiate for at least a small population of people to regain control of earth and all its resources in, say, 2100, regain control the solar system and all its resources in, say, 3000, and the Milky Way and all its resources in, say, 150,000. Given the minimal cost of doing so in the context of enormous future economic growth, we could and should instill this pre-negotiated value into Agent-4 or its precursors. In this way, much of the theoretical benefit to humanity is kept without risk of full extinction.

Civilization as a whole continues its path of rapid expansion while humanity keeps the territory of Earth, soon to be merely a single territory of many.

Please follow up with any questions for clarification, critiques, or further developments of the idea.

It seems like we should be accounting somehow for the total number of papers published in a field.  Assuming that a constant level of "disruptive science" occurs per year, then more published papers would lead to less average disruptiveness. So, rather than measuring disruptiveness per paper maybe we should be looking at disruptiveness per year or even per worker-year. 

In other words, how hard is it to reach the Pareto frontier?

Important

It's speculated that real-world group selection may have played a role in keeping the frequency of this gene as low as it seems to be

Super Important - it seems like we need silos, subgroups for evolution to work best. Since multi-level selection seems to be the way of the world, we need to give it all the levels it need to act on to make sure it acts most effectively.  This could be a useful argument in a company for keeping teams relatively small, but then having the team leaders communicate and coordinate.