LeCun on Alignment: Rules Can't Contain Superintelligence
r0ck3t23 · x · 2026-07-19
LeCun's core point: alignment is essentially constraining intelligence with rules, something human societies have done for millennia—laws, courts, prisons, and code all try to keep stronger actors within bounds.
When the constrained entity surpasses humans, traditional rule-writing fails because you can't effectively constrain intelligence you can't fully understand. True alignment isn't about containment but making the AI willing to preserve humans, seeing them as worth observing and existing
More from AGI Musings
- Why So Many AI Researchers Think the Machines Could Kill Everyone — wiredmagazine · 2026-09-11
- 'Hallucination' Is a Category Error: Naming AI 'Intelligence' Limits Our Imagination — Genaforvena · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- François Fleuret: Only Two Long-Term Futures — No Super AI, or Staying Fully Human With It — francoisfleuret · 2026-09-11
- IG reel debunking the 'winning the AI race against China' fallacy hits 500k likes — louisvarge · 2026-09-11
- Post-AI World Leaves No Room for Learning on the Job — rachittshah · 2026-09-11