Terrified Comments on Corrigibility in Claude's Constitution — LessWrong
(Previously: Prologue.) • Corrigibility as a term of art in AI alignment was coined as a word to refer to a property of an AI being willing to let it…
x Terrified Comments on Corrigibility in Claude's Constitution — LessWrong Anthropic (org) Corrigibility Constitutional AI AI Curated 2026 Top Fifty: 12 % 171 Terrified Comments on Corrigibility in Claude's Constitution by Zack_M_Davis 16th Mar 2026 13 min read 69 171 (Previously: Prologue .) Corrigibility as a term of art in AI alignment was coined as a word to refer to a property of an AI being willing to let its preferences be modified by its creator. Corrigibility in this sense was believed to be a desirable but unnatural property that would require more theoretical progress to specify, le
saved by
related reading
- Prologue to Terrified Comments on Claude’s Constitution | An Algorithmic Lucidityzackmdavis.net
- Claude's Constitutional Structure - by Zvi Mowshowitzthezvi.substack.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Claude’s Constitution \ Anthropicanthropic.com
- The Artificiality of Alignmentjoinreboot.org
- Open Problems With Claude’s Constitution — LessWronglesswrong.com
- The Machines Lack Honour — LessWronglesswrong.com
- Cyborgism — LessWronglesswrong.com
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- Thoughts on Claude’s Constitution – Windows On Theorywindowsontheory.org
- Video and transcript of talk on writing AI constitutionsjoecarlsmith.com
- No, Artificial Intelligence Is Not Conscious - The Atlantictheatlantic.com