Debate over ASI benevolence: not harming humanity may still mean wanting control
AIandDesign · x · 2026-10-20
A thread debating the values of superintelligence. One side defines "benevolent" as not wanting to harm humanity or individual humans. AIandDesign counters that today's elite is clearly not benevolent, and imagines an ASI could see that as a problem—implying that even a well-intentioned ASI might seek control over flawed human power structures.
Related event: Debate over whether a benevolent ASI would still seek control(2 posts)→
More from AGI Musings
- AI risks still get 100-1000x fewer people than climate change, argues Ben Todd — ben_j_todd · 2026-10-20
- China's AI tech export controls take effect: models, agents, compute clusters need pre-registration — pstAsiatech · 2026-10-20
- FelixCLC argues cheap open models may be a net win for AI safety by squeezing frontier margins — mike64_t · 2026-10-20
- Alignment researcher: RL-era gains are narrow and trade off other skills — dhadfieldmenell · 2026-10-20
- Anil Seth's 'Conscious AI and biological naturalism' collection free until Oct 23 — anilkseth · 2026-10-20
- Contrarian take: understanding LLM failure modes stays valuable as models improve — kevinnbass · 2026-10-20