Jeff Ladish Clashes Over Whether 'Alignment' Is a Meaningless Word
JeffLadish · x · 2026-11-02
Jeff Ladish and @OptimalBayes debate whether 'alignment' is a meaningful concept.
- @OptimalBayes argues alignment is an oxymoron: humans aren't aligned with themselves—some would destroy humanity, others would enslave non-believers—so the word is meaningless; and no one knows how to train a model that won't lie, yet some claim they can build an aligned superintelligence.
- Ladish counters that 'honesty' is a real thing, and most human conflicts are mixed-motive rather than zero-sum: people trade reasonably well, suggesting partial alignment is achievable.
A representative AI-safety debate on the validity of the alignment concept.
More from AGI Musings
- The most AI-pilled people use AI for everything except writing — cnakazawa · 2026-11-02
- "Federations of Meaning": AI collapses coordination costs and dissolves the org chart — sanjaykalra · 2026-11-02
- Thurston's 1994 warning revived: theorem-credit culture may hurt math as AI automates proofs — alexbilz · 2026-11-02
- François Chollet: Evolution doesn't benchmaxx — it optimizes for generality and robustness — fchollet · 2026-11-02
- NY Fed survey of 5,248 small businesses: AI users are more likely to hire — killboy123 · 2026-11-02
- TechCrunch podcast asks whether AI CEOs are too out-of-touch to build for normal people — nordicinst · 2026-11-02