CITATION — REFERENCE ENTRY
definition · soares2015corrigibility
- Citation
- soares2015corrigibility
- Claim ID
- definition
- Assertion
- An AI system is corrigible if it cooperates with what its creators regard as a corrective intervention, despite default incentives for rational agents to resist attempts to shut them down or modify their preferences.
- Quote
We call an AI system "corrigible" if it cooperates with what its creators regard as a corrective intervention, despite default incentives for rational agents to resist attempts to shut them down or modify their preferences.
- Quote language
- en
- Locator
- Abstract
Available in