A Godelian question: do dumb rocks defending against ASI need a proof of security?

jessi_cata · x · 2026-11-18

The author questions a scenario: could a future ASI explore the universe and hit a wall of rocks that—even being dumb and non-Turing-complete—cannot be blown up or gone around, with no penetration possible even by superintelligence?

By Godelian-style arguments, the author counters that this would require a "proof of security" of the rocks against all (or all bounded) adversaries—which is arguably far harder than just defending the rocks with a superintelligence of one's own.

Related event: ASI Thought Experiment: Can a Dumb Stone Wall Stop Superintelligence?(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →