Longterm Wiki

Singapore Consensus on AI Safety Research Priorities

in-effectInternational
Introduced 2025Wiki article →

Consensus document from the 2025 Singapore Conference on AI (SCAI), authored by 88 researchers from 11 countries, organizing AI safety research into a defence-in-depth framework across three areas: Assessment, Development, and Control.

Introduced
Committee
Floor Vote
Passed
Enacted

Related Legislation

Related Pages

Top Related Pages

Organizations

Frontier Model Forum

Approaches

Responsible Scaling Policies

Analysis

AI Safety Research Allocation ModelAI Safety Research Value ModelAI Safety Intervention Effectiveness MatrixPower-Seeking Emergence Conditions Model

Safety Research

InterpretabilityAI Control

Other

Yoshua BengioStuart Russell

Quick Facts

Introduced
2025
Status
Active consensus document
Scope
International

Sources

Tags

international-consensusai-safety-researchdefence-in-depthresearch-prioritiesscientific-cooperation