You can only guarantee zero mistakes by making zero predictions
burny_tech · x · 2026-11-22
Following the joke prompt demanding Claude "make no mistakes," the author offers a pointed rebuttal: zero mistakes can only be guaranteed by making zero predictions, and a theory that predicts nothing understands nothing — a classic take on the trade-off between reliability and generalization in AI systems.
More from AGI Musings
- Sandberg: weak concept generation means AI proofs will be long 'elementary' paths — anderssandberg · 2026-11-22
- Will 'compressing vast proofs' become an art? Sandberg thinks it might — anderssandberg · 2026-11-22
- Anthropic researcher: build state AI capacity instead of arguing about doom — joshua_saxe · 2026-11-22
- The 'Agent Platform of 2027' blueprint: actors, RBAC filesystems, inbox UX — yawnxyz · 2026-11-22
- AI practitioner: I can no longer predict AI capabilities with confidence — burny_tech · 2026-11-22
- 'There's never been a better time to go into math' amid AI boom — burny_tech · 2026-11-22