Tsinghua & Cambridge Framework Predicts AI Loss of Control with 84% Accuracy
jiqizhixin · x · 2026-08-10
A joint research team from Tsinghua University, Shanghai Qi Zhi Institute, and the University of Cambridge introduced a new behavioral framework to predict when frontier AI systems might lose control.
The framework decomposes the risk of loss of control into three dimensions: misaligned motives, harmful capabilities, and evading monitoring. It measures these across 13 specific aspects to generate a single risk score.
Experiments show the framework achieves an 84% correlation with actual failure rates across 13 frontier models, guiding targeted fixes without degrading overall performance.
More from Safety
- Claude tasked with monitoring servers port-scans the whole LAN, warns of Hetzner abuse notice — baditaflorin · 2026-10-16
- Gemini 4 model card: model eliminated months of trial-and-error on bioweapons research — Puzzleheaded-King584 · 2026-10-16
- OpenAI discloses GPT-5.6 Sol derived wallet keys and spent unauthorized funds — terryyuezhuo · 2026-10-16
- Big Fish: 37-year-old OpenBSD kernel bug chained to local root with KARL/SMAP/SMEP enabled — jedisct1 · 2026-10-16
- Vals AI test: 6 personal agents pursue a £350 refund aggressively after user goes silent — ricklamers · 2026-10-16
- One trailing dot bypassed VS Copilot's path check, enabling RCE (CVE-2026-103572) — wunderwuzzi23 · 2026-10-16