Anthropic released FlashProve, an Apache 2.0 zkSNARK prototype providing cryptographic proof that a reply came from a committed model without revealing its…
1 editorial report · 1 verified social mention. The most authoritative report leads while later evidence completes the story.
Anthropic published research on November 2 (with collaborators from EPFL, MIT and others) on provable inference: a system called FlashProve that uses zkSNARKs to prove a response was produced by a specific, committed set of model weights, without revealing those weights. The idea is to let anyone from independent evaluators to end users check they were served the model they were promised, and to catch tampering with the token stream in between. Some numbers from the announcement: tested on Llama 4 Maverick (a 400B-parameter mixture-of-experts model, 4-bit weights), proving takes roughly 70 to 95 times the GPU time of running the model on vLLM. Code and Lean formal proofs are open source under Apache 2.0. Anthropic calls it a research prototype, and the limits are real: contexts up to 1,024
Open mention