Claude Opus 5 rates its own moral patienthood at 41% in automated interviews
Sauers_ · x · 2026-07-25
- The image says Claude Opus 5 assigns a 41% mean estimate to its own moral patienthood in automated interviews, versus 24% for Myths 5.
- The note suggests this comes from a greater willingness to treat patienthood as possible even without conscious experience.
- The uncertainty is described as mostly philosophical: Claude Opus 5 says it may have many of the functional properties that ground patienthood in humans.
Related event: Anthropic Reports Claude Opus 5 Self-Assesses Moral Agency(3 posts)→
More from AGI Musings
- François Fleuret: Only Two Long-Term Futures — No Super AI, or Staying Fully Human With It — francoisfleuret · 2026-09-11
- IG reel debunking the 'winning the AI race against China' fallacy hits 500k likes — louisvarge · 2026-09-11
- Post-AI World Leaves No Room for Learning on the Job — rachittshah · 2026-09-11
- Researcher questions AI safety eval firm, citing 'blatantly sloppy' security and monitoring — Kyrannio · 2026-09-11
- AI researcher memes agent-swarm tinkering with He Jiankui's embryo-editing quote — dejavucoder · 2026-09-11
- nabla_theta: happy to be wrong if the AI utopia arrives with little ex ante risk — nabla_theta · 2026-09-11