Togelius: treating "solving alignment" as a goal is nonsensical and harmful
j_foerst · x · 2026-11-08
Game AI researcher Julian Togelius, in a candid post he admits writing instead of doing useful work, argues that treating "solving alignment" as a coherent goal is nonsensical and potentially harmful. Julian Foerster amplifies it as "another useful perspective" on why the framing of fully solving alignment is flawed. A provocative entry in the ongoing debate over whether alignment is a completable task.
More from AGI Musings
- The brain as the next UI: upcoming article charts BCI-meets-agentic-AI roadmap via earbuds — melnykowycz · 2026-11-08
- AI helps neurosurgery resident settle 22-year-old Crouzeix's conjecture in matrix analysis — IgorCarron · 2026-11-08
- NY Assemblyman urges Congress to ban Recursive Self-Improvement this year, citing 2027-28 AI lab timelines — rohanpaul_ai · 2026-11-08
- Radziwill says the quasi-Riemann proof fits in a tweet from the future — Singularitarian · 2026-11-08
- DeepMind exec says scientific discovery is undergoing a 'genuine phase transition' in pace — pushmeet · 2026-11-08
- IDC analyst: AI claims on social media distort completely after two reshares — perilli · 2026-11-08