Using LLMs to trace alchemical knowledge and decode 17th century letters
The author discusses the significant advancements in using frontier AI models like GPT-6 Sol and Opus 5.5 for historical research, beyond simple transcription. They propose that collaborative groups of historians and LLMs could solve complex historical problems, particularly those involving cryptography, multilingual reasoning, and large datasets.
Why it matters
This article highlights the transformative potential of advanced AI in humanities research, suggesting new methodologies for decoding historical texts and uncovering knowledge, which could lead to significant breakthroughs in understanding the past.
I’ve written previously about the pitfalls and use cases for AI in augmenting historical research, but things have changed significantly since 2024-25. Occasioned by the dueling releases of GPT-6 Sol and Opus 5.5 this week, I thought I’d share some early results with using these models not just to perform “research assistant” type functions like transcribing documents, but to try to actually solve existing historical problems.
The TLDR is that pairing historians working in collaborative groups with the current frontier models would, in my view, produce numerous advances in historical knowledge and interpretation. My guess is that many of these could end up being quite meaningful. This was not the case as recently as last year. I think AI labs, historical researchers, and funding agencies should start actively pursuing these collaborations.
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