Deterministic code, probabilistic meaning: on translating research back and forth with LLMs

Recently I had a conversation about how large language models are changing the way we do research, and one distinction kept coming back. Code is deterministic. Language, and the conceptual thinking we do in it, is probabilistic. Code runs. Language has to be interpreted. I have come to think this distinction is useful but slightly wrong, and the way in which it is wrong matters. In computational history we constantly move between these two registers....

November 2026 · Melvin Wevers