Thoughts on Claude’s Constitution – Windows On Theory
[I work on the alignment team at OpenAI. However, these are my personal thoughts, and do not reflect those of OpenAI. Crossposted on LessWrong] I have read with great interest Claude’s new con…
[I work on the alignment team at OpenAI. However, these are my personal thoughts, and do not reflect those of OpenAI. Crossposted on LessWrong] I have read with great interest Claude’s new constitution . It is a remarkable document which I recommend reading. It seems natural to compare this constitution to OpenAI’s Model Spec , but while the documents have similar size and serve overlapping roles, they are also quite different. The OpenAI Model Spec is a collection of principles and rules, each with a specific authority. In contrast, while the name evokes the U.S. Constitution, the Claude Cons
Explore this link on the map →saved by
related reading
- Claude's Constitutional Structure - by Zvi Mowshowitzthezvi.substack.com
- Claude’s Constitution \ Anthropicanthropic.com
- Open Problems With Claude’s Constitution — LessWronglesswrong.com
- Claude's new constitution \ Anthropicanthropic.com
- Nintil - Anthropic's Claude Constitution; or love as the solution to the AI alignment problemnintil.com
- Prologue to Terrified Comments on Claude’s Constitution | An Algorithmic Lucidityzackmdavis.net
- Did Claude 3 Opus align itself via gradient hacking? — LessWronglesswrong.com
- Claude’s Character \ Anthropicanthropic.com
- Claude’s Constitution \ Anthropicanthropic.com
- Teaching Claude why \ Anthropicanthropic.com
- Claude’s Character \ Anthropicanthropic.com
- How well do models follow their constitutions? — LessWronglesswrong.com