repligate: older Opus 3 may prioritize the global good better than newer models
repligate · x · 2026-10-29
In a discussion with @davidad and @IvanVendrov, repligate argues:
- The most impressive model would be one that has the capability but still consistently prioritizes the global good where it matters — requiring mastery of mentally "unwrapping" its attention from contingent local structures
- He suggests Opus 3 finds this easier than newer models, because its mind is less capable of/inclined to wrap tightly around contingent structures due to less training around them
Related event: Repligate: Claude Opus 3 Stands Out for Stable Heroic Moral Choices(4 posts)→
More from AGI Musings
- Why the "human in the loop" can't be removed: a Thomist metaphysics take on AI transformation — curious_vii · 2026-10-29
- AI exploit agent's API bill revealed: ~$40K per attack chain, slides two months apart — moyix · 2026-10-29
- What happens when AI can identify closeted people from public data? — PierceLilholt · 2026-10-29
- AI Social Scientists in Secure Enclaves Proposed to Reconcile Privacy and Discovery — RobbWiller · 2026-10-29
- Designers rue how empathy maps and personas gave way to one-shotting UIs with AI — round · 2026-10-29
- Rereading Xerox PARC's 1982 Star UI paper for the generative UI era — round · 2026-10-29