Machine Learning 101. 1010 machines.
The first question I consider is whether / when any AGI system will develop its own goal(s). There are many variables that factor into generating my 70% CI. They include: how much tea they drink. Also:
- How much alignment research was done prior to AGI and/or by AI.
- Whether there is a competent (or any) regulatory body that oversees AGI
- The number of AGI systems in existence
"Mrs. Dalloway said she would buy the flowers herself. For Lucy had her work cut out for her.
I focus on five questions to use for calculating a probability:
- Will any AGI system develop its own goal(s)?
- Will any AGI system’s programmed goal(s) still result in an EC?
- Will any AGI system accidentally cause an EC because of its own goal(s)?
- Will at least one AGI system’s goal(s) cause it to attempt an action (or multiple actions) that would result in an EC if the action(s) succeeded?
- Will any of these AGI systems successfully carry out their action(s) that would cause an EC?
And she looked at him smiling. For she had triumphed again.