STORY · VERKTOY_
Developer uses AI to map names from 500,000 Roman inscriptions
A developer has built a pipeline using Claude and Gemini to extract names from over 500,000 Latin inscriptions in the Epigraphic Database Clauss-Slaby, organizing them geographically. The system uses high-performance LLMs to oversee extraction region by region, with a target error rate below 1-2 percent.
WHY IT MATTERS
This demonstrates how LLMs can automate extensive academic historical work that traditionally requires manual expert classification. The project showcases the practical value of AI in the humanities when combined with domain-specific data.
SOURCES
MACHINE-GENERATED SUMMARY This summary is written by machine from the sources below. We sort and explain — but we are a way into the field, not the final word. Check the source when something matters to you.