Google launches world's first double-blind AI evaluation technology, ensuring benchmark test fairness based on an encrypted environment
Google, together with multiple institutions, launches the world's first double-blind evaluation for frontier proprietary AI models, relying on an encrypted privacy environment to avoid benchmark contamination while protecting both parties' data security and improving the credibility of AI model evaluation.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome