then the technical advisors at OPP must have a very specific approach to AI safety they are pushing very hard to get support for, but are unwilling or unable to articulate why they prefer theirs so strongly.
I don’t think there is consensus among technical advisors on what directions are most promising. Also, Paul has written substantially about his preferred approach (see here for instance), and I’ve started to do the same, although so far I’ve been mostly talking about obstacles rather than positive approaches. But you can see some of my writing here and here. Also my thoughts in slide form here, although those slides are aimed at ML experts.
I haven’t seen that your approach nor Paul’s necessarily conflicts with that of MIRI’s. There may be some difference of opinion on which is more likely to be feasible, but seeing as how Paul works closely with MIRI researchers and they seem to have a favorable opinion of him, I would be surprised if it were really true that OpenPhil’s technical advisors were that pessimistic about MIRI’s prospects. If they aren’t that pessimistic, then it would imply Holden is acting somewhat against the advice of his advisors, or that he has strong priors against MIRI that were not overcome by the information he was receiving from them.
I don’t think there is consensus among technical advisors on what directions are most promising. Also, Paul has written substantially about his preferred approach (see here for instance), and I’ve started to do the same, although so far I’ve been mostly talking about obstacles rather than positive approaches. But you can see some of my writing here and here. Also my thoughts in slide form here, although those slides are aimed at ML experts.
I haven’t seen that your approach nor Paul’s necessarily conflicts with that of MIRI’s. There may be some difference of opinion on which is more likely to be feasible, but seeing as how Paul works closely with MIRI researchers and they seem to have a favorable opinion of him, I would be surprised if it were really true that OpenPhil’s technical advisors were that pessimistic about MIRI’s prospects. If they aren’t that pessimistic, then it would imply Holden is acting somewhat against the advice of his advisors, or that he has strong priors against MIRI that were not overcome by the information he was receiving from them.