It follows from assuming sufficiently intelligent AIs will both:
Recognize that coordination gets them more of what they want
Be intelligent enough to overcome obstacles to coordination (whether through solving interpretability issues, using logical decision theory, or something else).
It follows from assuming sufficiently intelligent AIs will both:
Recognize that coordination gets them more of what they want
Be intelligent enough to overcome obstacles to coordination (whether through solving interpretability issues, using logical decision theory, or something else).
Related comment I made a while back.