Anthropic releases FlashProve, an open-source system for provable LLM inference
Anthropic published research on provable inference, in which a model provider commits to a specific model and attaches a cryptographic proof that each response came from it. The work centers on FlashProve, a zkSNARK-based prototype. Anthropic released five artifacts: the blog post, a technical report, a Claude-written protocol specification, executable code with a prover and two verifiers, and Lean proofs with an interactive visualizer.
Why it matters
Users and independent evaluators currently cannot confirm that a response came from the model they requested rather than a substitute picked by a routing service or an attacker. Anthropic's proofs would let a provider commit to a model and demonstrate each response came from it, without revealing the weights.
Sources
- PrimaryHacker News
Written by AIToolMaps from the source above and checked against it sentence by sentence.