Report details first double-blind eval of LLM using secure enclaves
Miles_Brundage · x · 2026-08-27
AVERI released a pilot report detailing the world's first double-blind evaluation of a proprietary language model, Gemini 2.5 Flash-Lite, in collaboration with Google DeepMind, OpenMined, and MLCommons. The evaluation used a secure enclave and Trusted Execution Environment (TEE) to ensure model weights and test prompts remained hidden from each other, addressing benchmark contamination and structural issues in independent auditing.
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