Research how to transfer knowledge from trained ML systems to humans.
An example: It was a great achievement when AlphaGo and later systems defeated human go masters. It would be an even greater achievement for the best computer go systems to lose to human go masters—because that would mean that the knowledge these systems had learned from enormous amounts of self-play had been successfully transferred to humans.
Another example: Machine learning systems that interpret medical X-ray images or perform other diagnostic functions may become better than human doctors at this (or even if not better overall, better in some respects). Transferring their knowledge to human doctors would produce superior results, because the human doctor could integrate this knowledge with other knowledge that may not available to the computer system (such as the patient’s demeanor).
From the x-risk standpoint, it seems quite plausible that a better ability to transfer knowledge would both allow humans to more successfully “keep up” with the AIs, and to better understand how they may be going wrong.
This line of research has numerous practical applications, and hence may be feasible to promote, especially with a bit of “subsidy” from those concerned about x-risks. (Without a subsidy, it’s possible that just enhancing the capability of ML systems would seem like the higher-return investment.)
This somewhat happenned in chess : today’s top players are much stronger than twenty years ago, mainly thanks to new understanding brought by the computers. Carlsen or Caruana would probably beat Deep Blue handily.
Research how to transfer knowledge from trained ML systems to humans.
An example: It was a great achievement when AlphaGo and later systems defeated human go masters. It would be an even greater achievement for the best computer go systems to lose to human go masters—because that would mean that the knowledge these systems had learned from enormous amounts of self-play had been successfully transferred to humans.
Another example: Machine learning systems that interpret medical X-ray images or perform other diagnostic functions may become better than human doctors at this (or even if not better overall, better in some respects). Transferring their knowledge to human doctors would produce superior results, because the human doctor could integrate this knowledge with other knowledge that may not available to the computer system (such as the patient’s demeanor).
From the x-risk standpoint, it seems quite plausible that a better ability to transfer knowledge would both allow humans to more successfully “keep up” with the AIs, and to better understand how they may be going wrong.
This line of research has numerous practical applications, and hence may be feasible to promote, especially with a bit of “subsidy” from those concerned about x-risks. (Without a subsidy, it’s possible that just enhancing the capability of ML systems would seem like the higher-return investment.)
This somewhat happenned in chess : today’s top players are much stronger than twenty years ago, mainly thanks to new understanding brought by the computers. Carlsen or Caruana would probably beat Deep Blue handily.