Critch’s comments support an opinion I’ve held since I started thinking seriously about alignment: that the language we use to describe it is too simple, and ignores the fact that “human” interests (the target of alignment) are not the monolith they’re usually presented as.
For your specific question about multi-multi, I only have limited access to the memeplex, so I’ll just share my thoughts. Multi-multi delegation involves: 1. Compromise / resolution of conflicts of interest between delegators. 2. Mutual trust in delegators regarding communication of interests to delegatees. 3. Equitable control between delegators. This could be lumped in with conflicts of interest, but deserves special attention. 4. Capacity for communication and cooperation between delegatees.
… and some other aspects I haven’t thought of. As far as I can see, though, the most important issues here would be addressed by consideration of single-multi and multi-single; multi-multi-specific problems will only be relevant when there are obstacles to communication between either delegators or delegatees (a conceivable future problem, but not a problem as long as the complexity of systems actually being constructed is limited).
Thanks! Trust, compromise, and communication are all items in Dafoe et. al. 2020, if you’re interested in exploring. I agree that primitive forms of these issues are present in multi-single and single-multi, it’s not clear to me whether we should think of solving these primitive forms then solving some sort of extension to multi-multi or if we should think of attacking problems that are unique to multi-multi directly. It’s just not clear to me which of those better reflects the nature of what’s going on.
Critch’s comments support an opinion I’ve held since I started thinking seriously about alignment: that the language we use to describe it is too simple, and ignores the fact that “human” interests (the target of alignment) are not the monolith they’re usually presented as.
For your specific question about multi-multi, I only have limited access to the memeplex, so I’ll just share my thoughts. Multi-multi delegation involves:
1. Compromise / resolution of conflicts of interest between delegators.
2. Mutual trust in delegators regarding communication of interests to delegatees.
3. Equitable control between delegators. This could be lumped in with conflicts of interest, but deserves special attention.
4. Capacity for communication and cooperation between delegatees.
… and some other aspects I haven’t thought of. As far as I can see, though, the most important issues here would be addressed by consideration of single-multi and multi-single; multi-multi-specific problems will only be relevant when there are obstacles to communication between either delegators or delegatees (a conceivable future problem, but not a problem as long as the complexity of systems actually being constructed is limited).
Thanks! Trust, compromise, and communication are all items in Dafoe et. al. 2020, if you’re interested in exploring. I agree that primitive forms of these issues are present in multi-single and single-multi, it’s not clear to me whether we should think of solving these primitive forms then solving some sort of extension to multi-multi or if we should think of attacking problems that are unique to multi-multi directly. It’s just not clear to me which of those better reflects the nature of what’s going on.