Debate: superintelligent AI can't be controlled, only shaped by what it wants

RazRazcle · x · 2026-09-05

RazRazcle argues on X that a superintelligent AI is not "controlled" by anyone — it does what it wants, and human influence lies only in shaping what it wants. He adds that survival and power-seeking (not necessarily replication) are selected for by long-horizon realistic RL environments, not just evolution, which is precisely why we must work to avoid such outcomes.

Related event: Debate Erupts Over Instrumental Convergence and Superintelligence Alignment(3 posts)→

Original post →

More from AGI Musings

AGI Musings channel →