NICK
CHIMICLES
COMPUTATIONAL
HISTORY
I work at the intersection of history, computer science, and archival technology. I build LLM systems over large archives of historical and government documents — semantic search, knowledge graphs, and evaluation — and apply them to intelligence-analysis problems.
Currently: technical co-lead on MIDLLMAT, a project under IARPA's BENGAL program with Columbia's History Lab.
RECENT WORK
HistoryLab AI
Conversational search over five million declassified government documents, built with Columbia's History Lab and presented at the Federal Depository Library Conference.
The Persistence of Precision
Alan J. Willen Prize-winning senior thesis reanalyzing the complete operational record of U.S. strategic bombing in WWII's European theater.
Alexander Database
Semantic search over the ancient sources on Alexander the Great, testing long-standing historiographical claims empirically.
Block-Bard
Blockchain-based collaborative storytelling where AI agents write branching narratives, kept coherent through distributed consensus.