GoKawiilEngineer uses AI search to mine 400 years of digitized archives for lost historical records
A software engineer, inspired by historian Benjamin Breen's AI-assisted discovery of a new dodo eyewitness account, built agentic AI workflows to search millions of digitized historical records in parallel. The project reportedly surfaced a previously unrecorded meteorite report, evidence of three 'lost' rhinos, and unrecorded volcanic eruptions. Breen's original find came from searching GLOBALISE's digitized Dutch East India Company archives, which cover 1602 to 1799.
GoKawiil's interpretation of the reporting above, not reported fact.
The project suggests large language models could become practical tools for combing vast, previously under-searched archives for small but genuine historical discoveries that specialists have overlooked. It points to a broader trend of non-historians using AI to contribute to niche academic fields, though the reliability of AI-surfaced findings would still need verification by domain experts. This could accelerate archival research generally, but also raises questions about error rates and proper historical vetting of AI-generated leads.
- An engineer applied AI search across digitized archives to find a forgotten meteorite report, three lost rhinos, and unrecorded volcanic eruptions.
- The effort was inspired by historian Benjamin Breen's discovery of a new 1615 dodo eyewitness account in Dutch East India Company records via the GLOBALISE project.
- The approach used chained AI models and agentic workflows to automate searching and filtering across multiple historical mysteries simultaneously.
Source: jessewaites.com, 2026-10-09
Published there as: “I Pointed AI at 400 Years of Archives. It Found a Forgotten Meteorites and More”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.