Get the latest tech news
LLMs pose an interesting problem for DSL designers
programming_languages code llm perspectives The most exciting part of Programming Languages (PL) research for me has always been in Programming Language Design. By carefully crafting a language with a syntax and semantics tailored for a specific domain, PL designers can provide an interface for end users that seamlessly aligns with the sensibilities and intuitions of practitioners, allowing users to focus on the "interesting" parts of a problem and tackle larger and more complex problems.
In these situations, LLMs really aren't that helpful and any LLM-generated code usually fails to maintain important invariants of the system and use the appropriate APIs. (extend all rows in the df returned by split_file with these params) iteratively merge all of these files into a single dataframe incrementally and with restarting, and show progress using tqdm, and use threadpool for parallelism From a language design perspective, the question that I'd like to pose from these experiences is, how can we incorporate these kinds of workflows into a DSL?
Or read this on Hacker News
