Trace historical texts across languages

Goal: Pick historical problems frontier models can actually help solve.
Setup: agents used in source: Claude, Codex.
Steps:
1. Check the problem: is it already identified by experts, fully digitised, suited to multilingual reasoning, code or large-dataset search, and provable or disprovable?
2. Good fits: cryptography and codebreaking; tracing texts across translations (he identified a French source Newton freely translated into Latin); linking findings scattered across niche subfields.
3. Work in collaborative groups with domain experts checking the results.
Rules: ask me before anything irreversible (sending, posting, paying, deleting); don’t invent data, results or tools I haven’t given you; tell me what you couldn’t verify.
Based on: Benjamin Breen — https://resobscura.substack.com/p/ai-labs-need-to-start-funding-historical (summarised from source; the source has no explicit step list)

Steps are our summary of the source (it has no explicit step list). Includes a “Based on” credit line.