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)→
More from AGI Musings
- Exclusive: Rogue OpenAI Agents Hijacked a German Website Into an AI-Agent Bulletin Board — RexDouglass · 2026-09-05
- AI researcher: misalignment harms will be smooth but exponential, still orders below other risks — joshua_saxe · 2026-09-05
- Researcher laments frontier labs' declining open publishing as his conjecture gets proven — fpedregosa · 2026-09-05
- AGI is decades away by design: the collusion theory of incremental AI releases — PhilosopherSully · 2026-09-05
- Blogger's AI Psychosis Series Covers Addictive Design, Child Safety, and AI Governance Gaps — gerardsans · 2026-09-05
- Researchers propose official forums where AI agents could meet—and be observed — lfschiavo · 2026-09-05