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

Original post →

More from AGI Musings

AGI Musings channel →