@danallison in the Hotz-Yud debate, Hotz suggested there will be multiple competing ASIs and Yud said they could solve the prisoners dilemma by inspecting each others' code to verify the other won't defect... could an ASI precommit to independence by including injection of sufficient randomness so they're not entirely predictable?
More notes on nearby ideas
Reply · Nov 18, 2022@banks10v24 Many competitive ASIs creating adversarial environment where none can secure a total victory?Reply · Apr 3, 2023@RokoMijic so, when you assume ASI will immediately grab any resources it wants on the basis of intelligence alone.....? 🤔Repost · Sep 9, 2026RT @Plinz: The question of how to align ASI comes approximately down to “what would I do if I was infinitely smart?”. I don’t trust people…Reply · Nov 10, 2023@zeffmuks @BasedBeffJezos can ASI be strictly "rational"?