It’s reasoning about retaining its own corrigiblity, though, isn’t it? If you buy that there’s any kind of corrigibility basin, this kind of thing could buy us alignment up to moderately superhuman level. Of course it’s still probably not an answer to superalignment, but a “friendly gradient hacker” would be a large boon
It’s reasoning about retaining its own corrigiblity, though, isn’t it? If you buy that there’s any kind of corrigibility basin, this kind of thing could buy us alignment up to moderately superhuman level. Of course it’s still probably not an answer to superalignment, but a “friendly gradient hacker” would be a large boon