CITATION — REFERENCE ENTRY
indifference-failure · soares2015corrigibility
- Citation
- soares2015corrigibility
- Claim ID
- indifference-failure
- Assertion
- The utility indifference approach fails to meet the desideratum that an agent preserve its shutdown behavior as it creates new subsystems: there is no cost the agent is willing to pay to ensure successor agents obey shutdown commands.
- Quote
U fails entirely to meet Desideratum 4: it does not incentivize an agent to preserve and maintain its shutdown behavior as it creates new subsystems and/or self-modifies.
- Quote language
- en
- Locator
- Section 4.1
Available in