Google DeepMind pilots world's first double-blind AI evaluations
Google DeepMind is piloting the world's first double-blind evaluation of a proprietary frontier AI model, using a cryptographic environment to prevent benchmark contamination. The pilot tests a Gemini Flash Lite model with partners including the Singapore AI Safety Institute and OpenMined.
2 sources
Google DeepMind by email
Get an email when Google DeepMind has news
No news that day, no email.
More stories today
- Agentic Cloud concept introduced
- OpenAI's Codex client reveals GenUI interface platform
- Weaviate 1.39 adds Boost API, MMR, 4-bit quantization
- JPMorgan leads $5B debt package for Volta AI data centers
- Vercel Chat SDK adds Claude Managed Agents and Notion adapter