As of: 2026-11-09 21:13 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/p/x-anthropicai-2117710942826123294/

# “New Anthropic research: progress on provable inference for large language models.”

Anthropic (@AnthropicAI), X, 2026-11-03.
Source: https://x.com/AnthropicAI/status/2117710942826123294

## Archived text

> 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).

Archived 2026-11-05 via fxtwitter (unofficial).
Counts: 651,405 views, 5,159 likes, 536 reposts, 625 replies (at fetch time)

## Cited in

- 2026-11-02: [Anthropic open-sources FlashProve, a zero-knowledge prototype that proves a response came from committed model weights](https://postcutoff.com/e/2026-11-02-anthropic-flashprove-provable-inference/)