What is Recursive Self-Improvement (RSI)? | Stanford HAI
Stanford
University
  • Stanford Home
  • Maps & Directions
  • Search Stanford
  • Emergency Info
  • Terms of Use
  • Privacy
  • Copyright
  • Trademarks
  • Non-Discrimination
  • Accessibility
© Stanford University.  Stanford, California 94305.

What is Recursive Self-Improvement (RSI)?

Recursive Self-Improvement (RSI) is the process by which an AI system improves its own capabilities, such as its code, architecture, training methods, reasoning, or use of tools, and then uses those enhanced capabilities to make further improvements. Each cycle could hypothetically produce a more capable system than the last. It is often discussed in relation to the possibility of rapid gains in AI capabilities, superintelligence, AI alignment, and AI safety.


Recursive Self-Improvement mentioned at Stanford HAI

Explore Similar Terms:

AGI (Artificial General Intelligence) | AI Alignment | AI Safety | Reinforcement Learning

See Full List of Terms & Definitions

Skip to content
  • About

    • About
    • People
    • Get Involved with HAI
    • Support HAI
    • Subscribe to Email
  • Research

    • Research
    • Research Programs
    • Grants
    • Marlowe (opens in new tab)
    • Student Affinity Groups
    • Centers & Labs
    • Research Publications
    • Research Partners
  • Education

    • Education
    • Executive and Professional Education
    • Government and Policymakers
    • K-12
    • Stanford Students
  • Policy

    • Policy
    • Policy Publications
    • Policymaker Education
    • Student Opportunities
  • AI Index

    • AI Index
    • AI Index Report
    • Global Vibrancy Tool
    • People
  • News
  • Events
  • Industry
  • Centers & Labs
Navigate
  • About
  • Events
  • AI Glossary
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us

Stay Up To Date

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Sign Up For Latest News

Enroll in a Human-Centered AI Course

This AI program covers technical fundamentals, business implications, and societal considerations.
Can AI Be Slowed Down? Stanford HAI Experts Weigh the Risks, Rules and Race Ahead
Shana Lynch
Sep 22
news

In a new series called Prompt Response, Stanford’s Surya Ganguli, Diyi Yang and Rob Reich examined emergent agent behavior, recursive self-improvement, independent evaluation and whether a kill switch can make advanced AI safer.

Can AI Be Slowed Down? Stanford HAI Experts Weigh the Risks, Rules and Race Ahead

Shana Lynch
Sep 22

In a new series called Prompt Response, Stanford’s Surya Ganguli, Diyi Yang and Rob Reich examined emergent agent behavior, recursive self-improvement, independent evaluation and whether a kill switch can make advanced AI safer.

Privacy, Safety, Security
Regulation, Policy, Governance
Generative AI
news