You can quantize any distribution. For the random distribution, you need to use 0.000… 01% quantilization to get anything useful at all. (In non-trivial environments, the vast majority of random actions are useless junk. If you have a humanoid coffee making robot, almost all random motor inputs will result in twitching on the floor.)
However, you can also quantalize over a model trained to imitate humans. Suppose you give some people a joystick and ask them to remote control the robot to make coffee. They manage this about half the time. You train the robot to be a 25% quantalizer. The top 25% of human actions will do better than humans.
This is technically equivalent to an imitator of humans, and an ASI that can only output 2 bits (which are used as a random seed for the human)
Though these descriptions imply different internal workings, which may indicate different probabilities of the AI using rowhammer.
You can quantize any distribution. For the random distribution, you need to use 0.000… 01% quantilization to get anything useful at all. (In non-trivial environments, the vast majority of random actions are useless junk. If you have a humanoid coffee making robot, almost all random motor inputs will result in twitching on the floor.)
However, you can also quantalize over a model trained to imitate humans. Suppose you give some people a joystick and ask them to remote control the robot to make coffee. They manage this about half the time. You train the robot to be a 25% quantalizer. The top 25% of human actions will do better than humans.
This is technically equivalent to an imitator of humans, and an ASI that can only output 2 bits (which are used as a random seed for the human)
Though these descriptions imply different internal workings, which may indicate different probabilities of the AI using rowhammer.
Yeah, I think this is the key point. Quantilizers are only safe or smart relative to some base distribution.