AI safety debate: do compute bounds limit the orthogonality of goals and intelligence?
Algon_33 · x · 2026-09-18
An X debate on the orthogonality thesis: Algon33 argues "true in practice" is imprecise — compute bounds exist, but why couldn't a merely human-level intelligence have wildly different goals, and why isn't the space of efficient goals big enough? jessicata counters that strong orthogonality is a claim about the goals-intelligence relationship and you can't assume infinite intelligence; compute bounds are intrinsic to intelligence, and if maximizing simple goals were easier than complex tractable ones, strong orthogonality could be false.
Related event: Debate Erupts Over the Orthogonality Thesis in AI Safety(8 posts)→
More from AGI Musings
- Alpha School investigation: 17 campuses on probation, Bill Ackman as shadow lead, Holmes involved — benjaminjriley · 2026-11-02
- Google's chief economist: AI will transform more jobs than it kills — gains come from redesigning workflows — danielrock · 2026-11-02
- Daniel Lemire: AI is exploding demand for boring compute, server CPUs to double — lemire · 2026-11-02
- Alignment researcher: the word "aligned" implies consistencies that don't exist — davidmanheim · 2026-11-02
- By 2035, Indian Parents Will Ask How Many Agents You Manage, Not Your Salary — theteknosaur · 2026-11-02
- Under 5% of US consumers pay for AI, yet compute demand is already forcing usage cuts — NinaDSchick · 2026-11-02