Hacker News new | ask | show | jobs
by LikesPwsh 35 days ago
Rather than telling the LLM "loop through these files", tell it "write a script to loop through these files", then hard-code that script somewhere.
2 comments

The models will eventually be able to know that they need to do that to get the thing done from natural language
"The models will eventually..." Yeah but they haven't, and it's been years now. Also who cares? We have problems right now that need to be solved.
First we gave LLMs access to bash commands. Now we give them access to customized commands which they can reuse. It's English language extending its claws into deterministic programming language. Now can we please have backtracking and dynamic programming like thinking loop built into English language or such orchestration prompts.