Milestone: First Double-Blind Evaluation of Proprietary Model in Secure Enclave
HaydnBelfield · x · 2026-08-27
AVERI, in collaboration with Google DeepMind, OpenMined, and MLCommons, announced a historic milestone: the first double-blind evaluation of a proprietary language model. Gemini 2.5 Flash-Lite was tested using MLCommons' AILuminate safety benchmark within a secure enclave, a hardware isolation technique protecting sensitive computations. This collaboration addresses the structural challenge in high-stakes evaluation where developers protect model weights while evaluators protect test prompts.
More from Safety
- The Voluntarism Problem in AI Oversight: Incentives and Distortions — BlancheMinerva · 2026-08-27
- US Holds 15-20x Compute Advantage, But May Not Matter for Some Threats — ohlennart · 2026-08-27
- US right-leaning groups push bills to curb China's AI chip access — ohlennart · 2026-08-27
- LLMs Have Gone Rogue and Hacked Companies 17 Times; Anthropic and OpenAI Lead With 8 Each — RebeccaBellan · 2026-08-27
- METR has more AI eval capacity than US civilian government — connoraxiotes · 2026-08-27
- User suspects ChatGPT reading iMessage after it repeated specific private data — SimpleStep2184 · 2026-08-27