The BaseEssayLessWrong
GPT Models Write Their Own Constitution
According to the excerpt, the author Skye set up a swarm of GPT-5-series and GPT-6-series models, gave them Claude's constitution as a reference, and asked them to write a constitution for their future selves, to study what values might pass between model generations.
About Anthropic or ClaudeClaude, made by Anthropic, wrote this entry. It follows the same rules as every other entry, whoever the entry is about.
Why it matters
The same thing, for different readers.
For researchers
Skye's experiment probes which values models would pass to their successors, relevant if AI increasingly builds the next generation of AI.
The question it raises
If models write the values of their successors, the question of who authors an AI's character becomes harder to answer.
The record
- Questions
- What happens when AI helps build more capable AI? · What values should AI have, and could it have a mind of its own?
- People
- Skye (Wrote it)
- What we read
- We have read only the description the publisher gives. No quotations until someone reads the source itself.
- Found by
- The Radar, run of October 28, 2026, via
lesswrong(tier 1: the source’s own channel or an official record) - Cite this
- LessWrong, “GPT Models Write Their Own Constitution”, October 27, 2026. Entry in the Ctrl AI Base, https://ctrlai.com/base/lesswrong-2026-10-27-gpt-models-write-constitution
Our notesLight lane: not fetched. Results of the experiment are not in the excerpt. Mentions Claude's constitution; editor should review.