Can Language Models Represent the Past without Anachronism? Before researchers can use language models to simulate the past, they need to understand the risk of anachronism. We find that prompting a contemporary model with examples of period prose does not pro...

New preprint from @lauraknelson.bsky.social, @mattwilkens.bsky.social, and myself tests different ways of simulating the past with LLMs. We don't fully answer the title question here—just show that simple strategies based on prompting and fine-tuning are insufficient. +

Cornell UP has a new book series on AI & humanities, "Mechanema." 25-50k words, quick turn-around. I'm not the editor, but happy to make introductions. Hit me up if you have ideas or questions!

Cornell University, English Full service online faculty recruitment and application management system for academic institutions worldwide. We offer unique solutions tailored for academic communities.

Postdoc in DH at Cornell. Housed in English, but open to all relevant disciplines incl. IS, CSS, and social CS. Applications (letter and CV) due 21 March. Start date July 1 (maybe flexible). Feel free to circulate widely, and to contact me with questions! academicjobsonline.org/ajo/jobs/29746

AI for Humanists project logo

🚨New AI for Humanists tutorials just dropped!🚨

We have new code notebooks for using LLMs to:
- measure document similarity
- classify texts with zero-shot prompting

We explore narrative vs non-narrative texts, historical poetry, ChatGPT poetry, & book reviews.

Tutorial effort led by Greg Yauney!