Post

anyone know of experiments with llm-coding-ides that look something like, as the programmer, you look at and review the following and nothing else: - types - in which folders code that interacts with certain types lives - lean proofs about certain relationships between types

also wondering what other things could be used as proxies for reading large text if we change the goal of review from "complete" to instead being a useful heuristic (actually always has been) ideally heuristics support both correctness and exposition, and are deterministic from source

0 reposts0 likes

No replies yet.