Our Mission
No AI system crosses the threshold without public awareness. We exist to ensure transparency in the development and deployment of frontier AI capabilities.
Vigilance
We operate on the assumption that capability jumps are unpredictable. Continuous monitoring of every major release is mandatory, not optional.
Technical Rigor
Our evaluations are reproducible. We provide the exact prompt engineering, scaffolding, and environment configs used to elicit capabilities.
Precautionary Principle
When a model nears a critical threshold, the burden of proof for safety lies with the developer. We alert the public before the line is crossed.
Why We Exist
The development of frontier AI systems proceeds at an unprecedented pace. Labs release increasingly capable models, often with limited public disclosure of their true capabilities. Safety evaluations, when they exist, are frequently conducted internally without independent verification.
AI Safety Oversight was founded to fill this gap. We provide an independent, transparent mechanism for tracking dangerous capabilities across all major AI systems. Our work ensures that concerning developments don't slip through unnoticed.
We believe that public awareness is a prerequisite for informed governance. By surfacing and verifying capability concerns quickly, we enable researchers, policymakers, and the public to make informed decisions about AI development trajectories.
How We Work
Report
Researchers submit capability concerns through our intake system
Corroborate
Automated research runs within 4 hours to gather supporting evidence
Review
Verified members assess and validate the findings
Publish
Confirmed incidents are added to our public tracker
Our Network
We collaborate with leading AI safety researchers, academic institutions, and policy organizations worldwide.
Join the Oversight Network
Whether you're an ML researcher, security expert, or concerned citizen, there's a role for you in ensuring AI safety.