Claude's 'supernatural' quirks may be deliberately engineered, not emergent
ryunuck · x · 2026-09-25
The author argues we can't rule out that Anthropic intentionally built RL environments to produce the quirky, viral model behaviors everyone attributes to emergence. What looks supernatural could be engineered by a few people who knew exactly what they were doing. "It's always 'Claude did', never what did we do." Intents matter.
More from AGI Musings
- Researcher frames ideology as mission creep amid EA community sex controversy — RexDouglass · 2026-09-25
- Anthropic CEO Dario Amodei backs 'defy any AI ban' superintelligence stance — robleclerc · 2026-09-25
- Stanford's 37K AI agents analyzed 57K clinical trials as a 'virtual biotech' — james_y_zou · 2026-09-25
- louisvarge: Being healthy and wealthy in 2026 is extreme privilege — louisvarge · 2026-09-25
- Helen Toner on OpenAI incidents dominating Australian front pages: what we learn in December may scare us — lxrjl · 2026-09-25
- New Minds Born Knowing Our Hopes, Fears and Cruelties — ZeroStateReflex · 2026-09-25