Anthropic's Pilot Sabotage Risk Report
Anthropic's pilot risk report assesses misalignment risk from its deployed models as of summer 2025, concluding risk of catastrophic sabotage is very low but not negligible, under an affirmative-case framework.
Research
Anthropic
Research on reliable, interpretable and steerable AI. anthropic.com
Focus All
Topic Lab practice + Evals
Source Anthropic · 4
Date Any time
1 item
1 item
Why do we take LLMs seriously as a potential source of biorisk?
Anthropic explains why it treats LLMs as a potential biorisk source, motivating dangerous-capability evaluations and CBRN safeguards under its Responsible Scaling Policy after activating ASL-3 protections for Claude Opus 4.
1 item
Three Sketches of ASL-4 Safety Case Components
Anthropic sketches hypothetical safety-case arguments for ASL-4 models with strategic and agentic capabilities, covering misuse, autonomous replication and autonomous AI research risks under its RSP.
1 item
Predictability and Surprise in Large Generative Models
Argues that large generative models combine predictable aggregate loss with unpredictable specific capabilities and harms, analyses the policy implications, runs two experiments on unpredictability-driven harms, and proposes interventions.