# Anthropic open-sources FlashProve to verify which AI model wrote a reply

> Original title: Anthropic just open-sourced FlashProve, which lets you check which AI model actually wrote a reply

- Source: Rohan Paul
- Published: 2026-11-03T20:15:49.000Z
- Bad Influence: https://badinfluence.news/items/ft134myqawj2li4pzy4pj550p
- Original: https://x.com/rohanpaul_ai/status/2117712372010004709

## Summary

Anthropic has open-sourced FlashProve, a cryptographic system that lets a server prove which AI model produced a given response. The post says it is far more efficient than prior open-source methods, and that a single Nvidia H100 produced proofs for Meta's Llama 4 Maverick at 110 tokens per second, each about 19MB, which a regular CPU checks in about 17 seconds. The author says the proofs could catch resellers serving a cheaper model and let safety evaluators confirm they are testing the model customers receive.

## Post

Anthropic just open-sourced FlashProve, which lets you check which AI model actually wrote a reply

checkable on an ordinary CPU.

e.g. if you pay for a top AI model through a reseller, you can’t check whether it quietly served a cheaper one. Anthropic’s FlashProve lets the server prove mathematically which model answered.

Anthropic tested it on Meta’s Llama 4 Maverick, a large 400B-parameter open model, where a single Nvidia H100 GPU produced proofs at 110 tokens/second, each about 19MB.

A regular CPU checks each proof in about 17 seconds, while VerInf, the only earlier system known to prove this model, made 93.6GB proofs that took almost a day to check.

Claude built the system, and because its code is hard to audit, the security guarantees are mathematically proved in Lean 4, a proof-checking language,

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWOgJ1ua0AAKtYr.jpg&mode=thumb&exp=1793923200&sig=b3787d568379619f)

## Quoted post @AnthropicAI

> New Anthropic research: progress on provable inference for large language models.
> 
> Here, we introduce FlashProve. Building on established cryptographic techniques, FlashProve allows developers to verify whether a given response came from a given AI model. It’s substantially more efficient than prior open-source methods for doing so. 
> 
> These proofs have a range of applications. They can, for instance, make it harder for attackers to hijack a chat, or enable safety evaluators to verify that the model they’re testing is the same one being served to customers.
> 
> For our full write-up, see here: https://www.anthropic.com/research/provable-inference
> 
> Further progress in provable inference will likely be an important part of improving trust in AI deployment. To that end, we're open-sourcing FlashProve’s code, here: https://github.com/anthropics/FlashProve
> 
> We’re grateful to our collaborators: Alessandro Chiesa, @GiacomoFenzi, @gwberg95, @miranda__christ, Rahul Dalal (http://rdalal.github.io) and Ben Mayer (@transmissions11).

https://x.com/AnthropicAI/status/2117710942826123294