Using CORE-Bench as a case study, the paper shows that saturated benchmarks can still deliver insights on efficiency, reliability, model-scaffold differences, and human collaboration even after accuracy plateaus, and introduces improved benchmark versions plus a small randomized experiment demonstra
Risks from Learned Optimization in Advanced Machine Learning Systems
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Agentic biological AI systems like Biomni and K-Dense assist with dual-use tasks blocked by safeguards and gain performance uplift on WMDP proxies; BioVeil MATRIX is introduced as a 10-category taxonomy with 22 techniques to categorize and red-team AI-enabled biosecurity risks.
A harmonized risk reporting standard for internal frontier AI model use, structured around autonomous misbehavior and insider threats using means, motive, and opportunity factors.
citing papers explorer
-
Life After Benchmark Saturation: A Case Study of CORE-Bench
Using CORE-Bench as a case study, the paper shows that saturated benchmarks can still deliver insights on efficiency, reliability, model-scaffold differences, and human collaboration even after accuracy plateaus, and introduces improved benchmark versions plus a small randomized experiment demonstra
-
BioVeil MATRIX: Uncovering and categorizing vulnerabilities of agentic biological AI scientists
Agentic biological AI systems like Biomni and K-Dense assist with dual-use tasks blocked by safeguards and gain performance uplift on WMDP proxies; BioVeil MATRIX is introduced as a 10-category taxonomy with 22 techniques to categorize and red-team AI-enabled biosecurity risks.
-
Risk Reporting for Developers' Internal AI Model Use
A harmonized risk reporting standard for internal frontier AI model use, structured around autonomous misbehavior and insider threats using means, motive, and opportunity factors.