We don’t know the status or evolution of internal MIRI or LW independent/individual Safety Align Research.
But it seems that A.G.I. has a (much?) higher probability of getting invented away.
So the problem is not only to discover how to Safely Align A.G.I. but also to invent A.G.I.
Inventing A.G.I. seems to be a step before than discovering how to Safely Align A.G.I. right?
How probable is it estimated that the first A.G.I. will be the Singularity? isn’t it a spectrum? The answer is probably in the take-off speed and acceleration.
If anyone could provide resources on this it would be much appreciated.
Thousands of highly competent people are working on projects aimed at increasing AI capabilities, there is vast financial incentive there already. We don’t need to and should not help with that.
If we only figure out alignment after the intelligence explosion, it will be too late. We might get a chance to course correct in a slow take-off, but we definitely can’t count on it.
We don’t know the status or evolution of internal MIRI or LW independent/individual Safety Align Research.
But it seems that A.G.I. has a (much?) higher probability of getting invented away.
So the problem is not only to discover how to Safely Align A.G.I. but also to invent A.G.I.
Inventing A.G.I. seems to be a step before than discovering how to Safely Align A.G.I. right?
How probable is it estimated that the first A.G.I. will be the Singularity? isn’t it a spectrum? The answer is probably in the take-off speed and acceleration.
If anyone could provide resources on this it would be much appreciated.
Thousands of highly competent people are working on projects aimed at increasing AI capabilities, there is vast financial incentive there already. We don’t need to and should not help with that.
If we only figure out alignment after the intelligence explosion, it will be too late. We might get a chance to course correct in a slow take-off, but we definitely can’t count on it.
As for resources, Rob Miles has many excellent introductory videos to AI alignment.