Why Corrigibility is Hard and Important (i.e. “Whence the high MIRI confidence in alignment difficulty?“)
Source
- Link: https://www.lesswrong.com/posts/ksfjZJu3BFEfM6hHE/why-corrigibility-is-hard-and-important-i-e-whence-the-high
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- other-corrigibility — Theory / Corrigibility