User maximization

https://arbital.com/p/30b

by Eliezer Yudkowsky Mar 31 2016

A sub-principle of avoiding user manipulation - if you see an argmax over X or 'optimize X' instruction and X includes a user interaction, you've just told the AI to optimize the user.


A sub-principle of avoiding user manipulation - if you've formulated the AI in terms of an argmax over $~$X$~$ or an "optimize $~$X$~$" instruction, and $~$X$~$ includes a user interaction as a subpart, then you've just told the AI to optimize the user. For example, let's say that the AI's criterion of action is "Choose a policy $~$p$~$ by maximizing/optimizing the probability $~$X$~$ that the user's instructions are carried out." If the user's instructions are a variable inside the formula for $~$X$~$ rather than a constant outside it, you've just told the AI to try and get the user to give it easier instructions.