Sounds promising. Are you interested in resilience to AI catastrophes or only prevention?
Doesn’t resilience imply reduction of x-risk?
I define x-risk as “risk of extinction and permanent drastic curtailment of humanity’s potential”
Can’t from the top of my head imagine a way to become more resilient to a catastrophe while not simultaneously reducing the x-risk.
Resilience as in reducing x-risk by improving our chances of surviving a catastrophe, as opposed to reducing x-risk by decreasing the chances of catastrophes occurring.
Sounds promising. Are you interested in resilience to AI catastrophes or only prevention?
Doesn’t resilience imply reduction of x-risk?
I define x-risk as “risk of extinction and permanent drastic curtailment of humanity’s potential”
Can’t from the top of my head imagine a way to become more resilient to a catastrophe while not simultaneously reducing the x-risk.
Resilience as in reducing x-risk by improving our chances of surviving a catastrophe, as opposed to reducing x-risk by decreasing the chances of catastrophes occurring.