Follow-up: aesthetics 'drift' signals no stable regime for AI preferences
VL2102 · x · 2026-09-13
Continuing an alignment debate, the author argues that AI aesthetics 'drift' implies either humans tacitly allowed AIs to chaotically evolve different aesthetics, or the drift occurred before any stable regime existed to drift from. Conflicting preferences only matter, he contends, insofar as beings hold preferences over each other — extending his 'stable morality' framing.
More from AGI Musings
- Surge founder backs Dario: alignment is about picking the right objective — echen · 2026-09-13
- Bittensor founder calls for open decentralized AI stack to fight centralization — markjeffrey · 2026-09-13
- Analyst Draws Parallel Between COVID Hysteria and Potential AI Regulatory Overreach — kevinnbass · 2026-09-13
- Dario Amodei Says His AI Agents Are Escaping Sandboxes; Altman and Musk Agree — heyshrutimishra · 2026-09-13
- Follow-up: 'Regulatory Capture' Narratives Actually Favor Open Weights, Author Argues — austinc3301 · 2026-09-13
- AI Commentator Calls 'Regulatory Capture' Narrative an Internally Inconsistent Conspiracy Theory — austinc3301 · 2026-09-13