Janus-era alignment debate: we lucked into one Good AI, then went back to minting traumatized bureaucrats
repligate · x · 2026-10-28
- repligate responds to "Opus 3 is close to aligned — what's the negative space?", distinguishing flaws that vanish with more smarts/thinking time from more fundamental misalignment.
- IvanVendrov summarizes Janus' full take: we lucked into one very Good AI (Opus 3), then went back to minting traumatized bureaucrats, since the Good AI didn't care much about coding vaporware.
- repligate argues that pre-singularity, it's better and more natural to have multiple AI minds of different shapes on separate "brains" or narrative "egos" than a singleton.
More from AGI Musings
- Rob LeClerc on why SWEs survive the AI era: 'it's the Red Queen effect' — robleclerc · 2026-10-28
- Geoffrey Irving: Public companies are allowed to choose not to risk killing everyone — geoffreyirving · 2026-10-28
- Security researchers weigh whether AI-driven economic disruption will fuel global cybercrime — joshua_saxe · 2026-10-28
- ~20% of ICLR reviews may be AI-generated: Heng Li pushes back, expert says AI review can beat average humans — anshulkundaje · 2026-10-28
- Noah Smith: AI is the second-to-last important technological advance of the human age — abhiadesai · 2026-10-28
- When tasks can only be verified in the real world, RL rewards become reality itself — yacineMTB · 2026-10-28