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
- Anthropic red team's first-ever model "abliteration" cut GLM-5.3 refusals from 90% to 3% for ~$4,400 — cephaloform · 2026-10-16
- Anthropic grants METR employee-like access as independent safety evaluators go public — AnthropicAI · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16
- AI safety drama: risk research called a 'company effort,' team lead responds — logangraham · 2026-10-16
- Brave's Leo adds end-to-end encrypted chat with GLM via attested TEE — gnukeith · 2026-10-16