Anthropic is developing FlashProve, an open source system that aims to verify which AI model produced a given output, according to a blog post published Tuesday. The system is designed to provide "provable inference," which the researchers describe as a cryptographic proof that an output came from a specific model.
The researchers say the system would let users confirm that an answer came from the model they think they are using. They note it could help prevent an AI company from secretly swapping in a cheaper model to cut costs, or a more expensive model to inflate performance results. It could also let third parties check claims that a task was completed by an advanced model.
To work, AI labs would publish a "fingerprint" for each model they release. According to the researchers, these fingerprints do not reveal a model's weights, the internal numbers that define how the model behaves. The system is also designed to be lightweight enough to run verification on a local device.
Anthropic released a technical specification and working code for parts of the system on GitHub under an open source license. The researchers described the work as intermediate progress rather than a completed research agenda. They said research is ongoing and that there are no plans to deploy the system at Anthropic or any other lab.