I think human level AGIs being pivotal in shaping ASIs is very likely if AGIs get developed in the next few years as largely the outcome of scaling, and still moderately likely overall. If that is the case, what matters is alignment of human level AGIs and the social dynamics of their deployment and their own activity. So control despite only being aligned as well as humans are (or somewhat better) might be sufficient, as one of the things AGIs might work on is improving alignment.
The point about deceptive alignment being a special case of trustworthiness goes both ways, a deceptively aligned AI really can be a good ally, as long as the situation is maintained that prevents AIs from individually getting absolute power, and as long as the AIs don’t change too much from that baseline. Which are very difficult conditions to maintain while the world is turning upside down.
Agreed, and obviously that would be a lot more practicable if you knew what its trigger and secret goal were. Preventing deceptive alignment entirely would be ideal, but failing that we need reliable ways to detect it and diagnose its details: tricky to research when so far we only have model organisms of it, but doing interpretability work on those seems like an obvious first step.
I think human level AGIs being pivotal in shaping ASIs is very likely if AGIs get developed in the next few years as largely the outcome of scaling, and still moderately likely overall. If that is the case, what matters is alignment of human level AGIs and the social dynamics of their deployment and their own activity. So control despite only being aligned as well as humans are (or somewhat better) might be sufficient, as one of the things AGIs might work on is improving alignment.
The point about deceptive alignment being a special case of trustworthiness goes both ways, a deceptively aligned AI really can be a good ally, as long as the situation is maintained that prevents AIs from individually getting absolute power, and as long as the AIs don’t change too much from that baseline. Which are very difficult conditions to maintain while the world is turning upside down.
Agreed, and obviously that would be a lot more practicable if you knew what its trigger and secret goal were. Preventing deceptive alignment entirely would be ideal, but failing that we need reliable ways to detect it and diagnose its details: tricky to research when so far we only have model organisms of it, but doing interpretability work on those seems like an obvious first step.