Using LLMs to trace alchemical knowledge and decode 17th century letters

(resobscura.substack.com)

30 points | by benbreen 2 hours ago

4 comments

  • z_rho_one 27 minutes ago
    Great use case of AI. Almost 4 years after the sensational release of GPT3.5, the best use case of AI is still being a powerful search engine that can gather information from all corners of the digital world.
    • monomania 4 minutes ago
      This. They still make a lot of mistakes, but their working memory and processing of a massive corpus of data are obviously beyond what any human could ever do. But when they flag something interesting for expert review you can do some really good stuff with it.

      Slightly tangential: One way I found of limiting impact from hallucinations was to get an LLM to produce, say, a Python program which processes the data in question. I was making some flashcards for astronomical data and tried to get an LLM to put it all together in Typst, but correcting the hallucinations got to be too much to handle, so I had it write a Typst template and also a Python program which would convert the ephemerides data fields to a Typst file sourcing the template. Worked flawlessly.

  • riazrizvi 51 minutes ago
    This is a strong application of LLMs IMO. They are idea machines. Historical ways of thinking give us different paths to explore the world through.
  • whythismatters 34 minutes ago
    Great post, thank you! So, let's resolve ancient Near East chronology and determine an absolute date for the sack of Babylon?
  • b112 36 minutes ago
    I'm guessing it wasn't Claude 5.5, not with the "dangerous" nature of this work.