I think Daniel may be speaking of the moral hazard of AI developers having access to corrigible-to-them AI internally and deploying prosocial-according-to-them AI externally.
What do you mean by moral hazard here? (I agree that if developers have fully corrigible AI internally then it should have a separate model implementing refusals and/or whistleblowing)
Well, A (the developer) has substantial discretion over a powerful technology which has impact on both A and B (other people), which is a moral hazard. This applies in both cases in different ways (corrigible-to-them internal-only access and prosocial-according-to-them external deployment). In my reading of Daniel’s response, the hypothesis is that in both contexts the tech would be able to exert takeover-assisting or -implementing influence.
I agree that some sort of monitoring scheme internally might mitigate that. And some sort of visible spec with auditing and/or other validation might help in the external case.
I think Daniel may be speaking of the moral hazard of AI developers having access to corrigible-to-them AI internally and deploying prosocial-according-to-them AI externally.
What do you mean by moral hazard here? (I agree that if developers have fully corrigible AI internally then it should have a separate model implementing refusals and/or whistleblowing)
Well, A (the developer) has substantial discretion over a powerful technology which has impact on both A and B (other people), which is a moral hazard. This applies in both cases in different ways (corrigible-to-them internal-only access and prosocial-according-to-them external deployment). In my reading of Daniel’s response, the hypothesis is that in both contexts the tech would be able to exert takeover-assisting or -implementing influence.
I agree that some sort of monitoring scheme internally might mitigate that. And some sort of visible spec with auditing and/or other validation might help in the external case.