alt Hacker NewsDon’t ask the LLM to do that directly: ask it to write a program to answer the question, then have it run the program. It works much better that way.
Replies
xigoi • today at 6:20 AM
If the LLM is intelligent, why can’t it figure out on its own that it needs to write a program?
➕ show 1 reply
But for lisp, a more complex solution is needed. It's easy for a human lisp programmer to keep track of which closing parentheses corresponds to which opening parentheses because the editor highlights parentheses pairs as they are typed. How can we give an LLM that kind of feedback as it generates code?