Beat me to it. Yes the lesson is perhaps to not create prediction markets that incentivise manipulation of that market towards bad outcomes. The post could be expanded to a better question of, given that prediction markets can incentivise bad behaviour, how can we create prediction markets that incentivise good behaviour?
This reminds me somewhat of the potentially self-fulfilling prophecy of defunding bad actors. E.g. if we expect that global society will react to climate change by ultimately preventing oil companies from extracting and selling their oil field assets. Then those assets are worth much less than their balance sheets claim, so we should divest from oil companies. That reduces the power of oil companies that then makes climate change legislation easier to implement and the prophecy is fulfilled. Here the share price is the prediction market.
I’d ask the question whether things typically are aligned or not. There’s a good argument that many systems are not aligned. Ecosystems, society, companies, families, etc all often have very unaligned agents. AI alignment, as you pointed out, is a higher stakes game.
Your proofs all rely on lotteries over infinite numbers of outcomes. Is that necessary? Maybe a restriction to finite lotteries avoids the paradox.
Leinbiz's Law says that you cannot have separate objects that are indistinguishable from each other. It sounds like that is what you are doing with the 3 brains. That might be a good place to flesh out more to make progress on the question. What do you mean exactly by saying that the three brains are wired up to the same body and are redundant?
I’ve always thought that the killer app of smart contracts is creating institutions that are transparent, static and unstoppable. So for example uncensored media publishing, defi, identity, banking. It’s a way to enshrine in code a set of principles of how something will work that then cannot be eroded by corruption or interference.
There is the point that 80% of people can say that they are better than average drivers and actually be correct. People value different things in driving, and optimise for those things. One person’s good driver may be safe, someone else may value speed. So both can say truthfully and correctly that they are a better driver than the other. When you ask them about racing it narrows the question to something more specific.
You can expand that to social hierarchies too. There isn’t one hierarchy, there are many based on different values. So I can feel high status at being a great musician while someone else can feel high status at earning a lot, and we can both be right.
I think a problem you would have is that the speed of information in the game is the same as the speed of, say, a glider. So an AI that is computing within Life would not be able to sense and react to a glider quickly enough to build a control structure in front of it.
I’d say 1 and 7 (for humans). The way humans understand go is different to how bots understand go. We use heuristics. The bots may use heuristics too but there’s no reason we could comprehend those heuristics. Considering the size of the state space it seems that the bot has access to ways of thinking about go that we don’t, the same way a bot can look further ahead in a chess games than we could comprehend.
There are extra costs here that aren’t being included. There’s a cost to maintaining the pill box - perhaps you consider that small but it’s extra admin and we’re already drowning in admin. There’s a cost to my self identity of being a person who carries around pills like this (don’t mean to disparage it, just not for me). There’s also potentially hidden costs of not getting ill occasionally, both mentally and physically.