Anthropic open-sources FlashProve, a prototype that proves which AI model produced a reply
RESEARCHAnthropicredteam/daily · 1 source
- Severity
- Info
- Sources
- 1
What happened
Anthropic's Frontier Red Team, working with researchers at EPFL, MIT and StarkWare, released FlashProve as open source under Apache 2.0. The prototype produces cryptographic proofs that a particular language model generated a particular reply, addressing the problem that callers of hosted APIs cannot confirm which model answered them.
For IT people · Written by AI from 1 source · Wrong?
What to do
- Review the FlashProve repository and protocol specification on GitHub if you need to verify which model served your API requests.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
Help Net Security
Who and what is in it
Companies