In 2018, our founders invented STARKs. We then put them into production to scale blockchains and bring privacy onchain. Now Anthropic is building on that same cryptography to make AI inference verifiable. Love seeing STARK research find new applications beyond blockchains. https://x.com/AnthropicAI/status/2117710942826123294 Quoted @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).