Using Opus 5.5 to discover a new eyewitness record of the dodo
Security researcher Carter Church used AI models to analyze historical archives and discover a 1615 Dutch report regarding dodo hunting. The process involved using semantic search and frontier models to process large datasets of historical documents.
Why it matters
This demonstrates the growing utility of AI in academic research and historical sleuthing, enabling the processing of massive archives that were previously difficult to search.
Another day, another historical cipher broken by a frontier model. Yesterday, the security researcher Carter Church announced that he had used GPT-6 Astra (working on the problem for six hours) to break a Napoleonic-era cipher that had previously resisted all decryption attempts.
Church’s post on the subject is an interesting example not just of a reproducible methodology, but also of how to vibe code an information-dense writeup that is notably different from any traditional academic aesthetic, but which actually does surface primary sources and meaningful information in a fairly deep way:
The aesthetic weirdness is just the tip of the iceberg here. What I notice most about these forays into historical sleuthing using AI (and my own attempts at same) is the epistemological weirdness of how current frontier models now operate when given historical research tasks.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in