Scaling Laws For Scalable Oversight
Apr 25, 2025·
,,,·
1 min read
David Baek
Joshua Engels
Subhash Kantamneni
Max Tegmark
Image credit: UnsplashAbstract
For the first time, we propose a framework that quantifies the probability of successful oversight as a function of the capabilities of the overseer and the system being overseen. We also find scaling laws in four different oversight games that approximate how domain performance depends on general AI system capability.
Type
Publication
In NeurIPS 2025 (Under Review)
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Create your slides in Markdown - click the Slides button to check out the example.
Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.
