Sourceblog posttext stored
Corrigibility
paulfchristianoDate not recordedOriginal︎ ↗Archived copy
Claims1
ExaminationsNone
Text68 sections
VersionsOne known
CopiesNone recorded
CorrectionsNone recorded
Facts checked Nov 14, 2026ReachNo copies recorded
StructureIn 1 claim's map0 sources downstream across 1 claim
EvidenceNot yet read
ReviewsNot reviewed
Examinations
None recorded. An examination is commissioned by a claim’s Steward for what its claim rests on; a review of the document for its own sake is asked for as a request bearing on it.
Text82 passages · 0 marked
No examination yetMarked passage
No claim quotes it yet.
Not found in the text 1
As quoted
But a corrigible agent prefers to build other agents that share the overseer's preferences — even if the agent doesn't yet share the overseer's preferences perfectly. After all, even if you only approximately know the overseer's preferences, you know that the overseer would prefer the approximation get better rather than worse. ... Corrigible systems want to design more corrigible and more capable successors.
An approximately aligned AI system will preserve or improve alignment in more capable successors it helps build or oversee.
Not yet read by this claim’s Steward.
Lineage across 1 claim
Draws on · none recorded
This source
Drawn on by · none recordedCorrigibility
in 1 claim's map
Record
- Kind
- blog post
- Authors
- paulfchristiano
- Publisher
- Not recorded
- Published
- Not recorded
- DOI
- None
- Link
- https://www.lesswrong.com/posts/fkLYhTQteAu5SinAc/corrigibility
- Archived copy
- https://web.archive.org/web/20260624105308/https://www.lesswrong.com/posts/fkLYhTQteAu5SinAc/corrigibility
- Stored text
- 26,229 characters, retrieved Nov 14, 2026 · 68 sections, 82 passages
- Claims extracted
- Not recorded
- Versions
- One known
- Copies
- None recorded
- Corrections
- None recorded
- Facts checked
- Nov 14, 2026
History 3
- Nov 14, 2026DividedSegmenter · Divided into 149 parts by its own structure
- Nov 14, 2026FactsFacts fetcher · Facts looked up
- Nov 14, 2026Entered the graphEntered the graph; copy stored