Using LLMs to trace alchemical knowledge and decode 17th century letters
Summary
The article discusses using frontier AI models (like GPT-6 Astra and Opus 5.5) to assist historical research, including cryptography, text transmission, and alchemical knowledge. It presents case studies (deciphering codes, tracing texts across translations, and linking disparate sources) and argues for funded, collaborative efforts between historians and AI labs to push historical understanding forward. It also weighs the limitations and emphasizes the importance of access to digitized primary sources and disciplined, verifiable results.