Skip to content
Technical AI Safety Knowledge Hub SAFE | Responsbile | Human Centered AI
Explore the Library
  • Home
  • About
    • Mission and principles
    • Profile of the Founder
    • People & Community
    • How to contribute
    • Contributors
    • Editorial policy
    • Corrections and takedown
  • Explore AI Safety
  • Knowledge Library
  • Research & Projects
    • Research projects
    • Insights and articles
  • Courses & Workshops
    • Learning pathways
    • Workshops
  • Events
  • Contact Us
  1. Home
  2. Explore AI Safety
  3. Scalable Oversight

Technical AI Safety

Scalable Oversight

Supervising systems whose outputs are hard for humans to evaluate directly.

Everything 7 Library 5 Projects 2
Archived

Piloting the first empirical measurement of gradual AI disempowerment by evaluating supervisor “override-capacity” and calibration loss in deployed legal workflows

Gradual disempowerment describes a risk that humans lose meaningful control not through a single failure, but through many small hand-overs of judgement to AI systems. The idea is…

Implementation prototype
  • AI Law and Policy
  • Human Agency
Proposed

Can Non-Experts Oversee AI-Assisted Legal Review?

A proposal to test, with a small controlled study, whether reviewers with limited legal training catch more errors in AI-generated contract summaries when given structured oversight aids such…

No results yet
  • AI Law and Policy
  • Human Agency

Related topics

  • Agent Safety and Control
  • AI Alignment and Specification
  • Mechanistic Interpretability
  • Model Evaluations
  • Robustness and Reliability
Technical AI Safety Knowledge Hub SAFE | Responsbile | Human Centered AI

An independent platform for AI Safety research, education and governance. Summaries are editorial and are not legal or professional advice.

Explore

  • Start here
  • Knowledge Library
  • Research projects
  • Insights

Learn and take part

  • Learning pathways
  • Workshops
  • Events
  • People and community

Contact

  • contact@aigovernance.lk
  • Contact page
  • Who runs this platform
  • Contribute

With past support from

BlueDot Impact Amazon Web Services (AWS)

© 2026 Technical AI Safety Knowledge Hub. SAFE | Responsbile | Human Centered AI

  • Editorial policy
  • Corrections and takedown
  • Accessibility
  • Privacy policy
  • Contact