Anthropic unveils open-source FlashProve to cryptographically prove which AI model made an output
thione · x · 2026-11-10
Anthropic and university researchers introduced FlashProve, an open-source system for "provable inference": a cryptographic proof guaranteeing a given output came from a specific model. Like email signatures, it can block labs from secretly swapping in cheaper models to cut costs or pricier ones to inflate benchmark results. There are no deployment plans yet.
More from Safety
- Catherine Olsson revisits the spec gaming master list of AI reward-hacking examples — catherineols · 2026-11-10
- HN debate: permission-scoped subaccounts as the missing safety layer for AI agents — vboykis · 2026-11-10
- Claude Code settings files expose thousands of secrets on GitHub — Ars Technica AI · 2026-11-10
- Oxford releases 180-page mechanistic interpretability handbook with 51 methods and 19 notebooks — Hesamation · 2026-11-10
- Zero data retention is why enterprises self-host: Azure ZDR requires approval, no ZDR for fable — HanchungLee · 2026-11-10
- Stanford SIEPR to host forum on economic policy in the age of AI on Nov 12 — mioana · 2026-11-10