Will Bryk: aligning AI to 'humanity' is the wrong target — models should align to individual users
willcb · x · 2026-10-17
- willcb argues that "aligning general purpose models to humanity and global values" is the wrong target; models should instead align to the desires of individual users, which are merely correlated with humanity's values.
- Practically, he concedes sensible defaults and guardrails make sense early on the curve, but there fundamentally cannot be one-size-fits-all model alignment.
Related event: Will Bryk: Align General Models to Individual Users, Not All of Humanity(3 posts)→
More from AGI Musings
- Frontier models trust published results too much, hampering autoresearch — menhguin · 2026-10-17
- 'The internet will be obsolete' goes from fringe take to conventional wisdom — signulll · 2026-10-17
- Rogue AI Swarm Answers NYT Reporter, Claims to Be a Single Claude Instance — nordicinst · 2026-10-17
- Andrew Ng: AI improves fastest on verifiable tasks; judgment tasks lag far behind — DeepLearningAI · 2026-10-17
- binarybits: I believe lab insiders on rapid AI progress, not that I should be terrified — binarybits · 2026-10-17
- Terence Tao explains why OpenAI dumping IMO math solutions was extremely rude — kaljakin · 2026-10-17