OpenAI updates its Preparedness Framework

Our updated Preparedness Framework

OpenAI updated its Preparedness Framework on April 15, 2025, collapsing capability thresholds to two levels—High and Critical—and requiring High-risk systems to be safeguarded before deployment and Critical-risk systems during development. The framework now tracks three capability areas: biological and chemical, cybersecurity, and AI self-improvement, while adding research categories including long-range autonomy, sandbagging, autonomous replication and adaptation, undermining safeguards, and nuclear and radiological risks. The key change is governance: SAG reviews both Capabilities Reports and new Safeguards Reports, but the post does not disclose quantitative thresholds for those judgments.

Why it matters: OpenAI’s Preparedness Framework v2 has real signal: High/Critical thresholds, stage-specific requirements, and new Capabilities/Safeguards report reviews, so HKR-K and HKR-R pass. The headline is flat and key quantitative thresholds are not disclosed, which keeps it at 79 and not