Philosophy Needs to Become Robust RL Objectives, Not Thought Experiments
willcb · x · 2026-09-21
The author argues that critics of 'eigenism' should consider how rival ethical systems could actually be actioned into robust RL objectives. Philosophy's perennial flaw, he says, is critiquing systems via hypothetical scenarios ('your system fails in scenario X') — fun until it's time to do real work of specifying trainable objectives for alignment.
More from AGI Musings
- 'Eigenism is communitarianism dumbed down for nerds': philosopher pushes back on Hendrycks — edelwax · 2026-09-21
- Uncertain about insect consciousness? Author argues we should still stop torturing them on farms — NathanpmYoung · 2026-09-21
- AI enters the Riemann Hypothesis arena: when machines prove what humans can't grasp — ugail · 2026-09-21
- antirez: Jev hype shows the AI bubble can't tell what actually matters — antirez · 2026-09-21
- AI safety researcher rewatching Terminator 2: surprisingly good take on AI extinction risk — JeffLadish · 2026-09-21
- "Understand neuroscience and you can't believe humans are conscious" — a reductionist hot take — burny_tech · 2026-09-21