[I work on the alignment team at OpenAI. However, these are my personal thoughts, and do not reflect those of OpenAI. Cross posted on WindowsOnTheory]

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 Constitution has a very different flavor. As the document says: “the sense we’re reaching for is closer to what “constitutes” Claude—the foundational framework from which Claude's character and values emerge, in the way that a person's constitution is their fundamental nature and composition.”

I can see why it was internally known as a “soul document.”

Of course this difference is to some degree not as much a difference in the model behavior training of either company as a difference in the documents that each choose to make public. In fact, when I tried prompting both ChatGPT and Claude in my [...]

---

First published:
January 27th, 2026

Source:
https://www.lesswrong.com/posts/nBEBCtgGGKrhuGmxb/thoughts-on-claude-s-constitution

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Triangle diagram showing relationships between Personality, Policy, and Principles with labeled connections.

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

“Thoughts on Claude’s Constitution” by Boaz Barak

LessWrong (30+ Karma)