As an experienced LLM user, I don't use generative LLMs often

Re:As an experienced LLM user, I don't use generative LLMs o... by protocolture on Monday May 05, 2025 @07:24PM (#43900358)

>Although pandas is the standard for manipulating tabular data in Python and has been around since 2008, I’ve been using the relatively new polars library exclusively, and I’ve noticed that LLMs tend to hallucinate polars functions as if they were pandas functions which requires documentation deep dives to confirm which became annoying.

Funnily enough I was trying to deal with some lesser used parts of pandas via LLM and it kept sending me back through a deprecated function for everything. It was quite frustrating.

[ Parent | on HN ]

Re:As an experienced LLM user, I don't use generative LLMs o... by __mharrison__ on Tuesday May 06, 2025 @06:33AM (#43903527)

This is because the training data for pandas code is not great. It is a lot of non programmers banging keys until it works or a bunch of newbie focused blog posts that endorse bad practices.

[ Parent | on HN ]

Re:As an experienced LLM user, I don't use generative LLMs o... by protocolture on Tuesday May 06, 2025 @08:16PM (#43910983)

That tracks

[ Parent | on HN ]