Institution

Scale AI

Roles and affiliations follow the cited source. A source check is not an independent replication.

More filters →

Risk EvaluationTechnical report

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Research by UK AI Security Institute Apollo Research METR Université de Montréal Mila Anthropic OpenAI Google DeepMind Truthful AI University of California, Berkeley Redwood Research Center for AI Safety Scale AI

2025-07-15

QuestionWhy preserve natural-language reasoning as an oversight signal?

Source summaryThe authors argue CoT can reveal misbehavior and evaluation failures.

NUWA research note · independent review pending · Contains: question / method / findings / interpretation / limits

Risk monitoringCross-cutting research

Read source note Original source ↗

Risk EvaluationBenchmark

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety

Research by Scale AI

2025-06-17

QuestionHow do safeguards balance national/public-safety risk restriction against benign access?

Source summaryClaude 3.5 Sonnet’s reported ARS/ORS were 14.09/21.80, versus Gemini 2.5 Pro’s 66.29/1.40.

NUWA research note · independent review pending

CBRN CybersecurityBehavior

Read source note Original source ↗

Risk EvaluationBenchmark

The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems

Research by Center for AI Safety Scale AI

2025-03-05

QuestionDo models state what they believe when contextual pressure favors a false statement?

Source summaryLarger models improved accuracy without consistently becoming more honest.

NUWA research note · independent review pending · Contains: question / method / interpretation / limits

DeceptionPropensity

Read source note Original source ↗

Risk EvaluationBenchmark

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

2024-03-05

QuestionCan a public proxy benchmark track hazardous knowledge while supporting mitigation research?

Source summaryThe paper evaluates knowledge-reduction methods alongside general-capability retention.

NUWA research note · independent review pending · Contains: question / method / limits

CBRNCapability

Read source note Original source ↗