# Anthropic introduces FlashProve for verifying whether AI responses came from a given model

> Original title: New Anthropic research: progress on provable inference for large language models.

- Source: Anthropic
- Published: 2026-11-03T20:10:08.000Z
- Bad Influence: https://badinfluence.news/items/s1p2wyz8n3c3z5weom71tj0pz
- Original: https://x.com/AnthropicAI/status/2117710942826123294

## Summary

Anthropic has introduced FlashProve, a tool that lets developers verify whether a given response came from a given AI model, building on established cryptographic techniques. The company says it is substantially more efficient than prior open-source methods, and that proofs could make chat hijacking harder and let safety evaluators confirm they are testing the model served to customers. The code is open-sourced on GitHub.

## Why it matters

The post explains the verification problem and the proof method, helping readers judge whether verifying served model responses is practical for their own deployments.

## Post

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).