Would minimising the number of CPU cycles work as a lazy incentive.
This assumes that lesser CPU cycles will produce an outcome that is satisified rather than optimised, though in our current state of understanding any optimisation routines take a lot more computing effort than ‘rough enough’ solutions.
Perhaps getting the AGI’s to go Green will kill two birds with one stone.
Would minimising the number of CPU cycles work as a lazy incentive.
This assumes that lesser CPU cycles will produce an outcome that is satisified rather than optimised, though in our current state of understanding any optimisation routines take a lot more computing effort than ‘rough enough’ solutions.
Perhaps getting the AGI’s to go Green will kill two birds with one stone.
This has problems with the creation of subagents: http://lesswrong.com/lw/lur/detecting_agents_and_subagents/
You can use a few CPU cycles to create subagents without that restriction.
It can be difficult to impossible to know how many CPU cycles a problem will take to solve before you solve it.