Why Corrigibility is Hard and Important (i.e. "Whence the high MIRI confidence in alignment difficulty?")
Original: https://www.lesswrong.com/posts/ksfjZJu3BFEfM6hHE/why-corrigibility-is-hard-and-important-i-e-whence-the-high
Metadata
- authors
- Raymond Arnold
- Eliezer Yudkowsky
- Nate Soares
- citation
- locator_schemes
- id
- raemon_yudkowsky_soares.corrigibility-hard-important
- kind
- essay
- language
- en
- published_at
- 2025-09-30
- title
- Why Corrigibility is Hard and Important (i.e. "Whence the high MIRI confidence in alignment difficulty?")
- url
- https://www.lesswrong.com/posts/ksfjZJu3BFEfM6hHE/why-corrigibility-is-hard-and-important-i-e-whence-the-high
Cited by (1)