Large Language Models as Optimizers

Re:Large Language Models as Optimizers by sytelus on Friday September 08, 2023 @03:12PM (#37438045)

This is very nicely done and much more clear to follow than the paper. One question: Does LLM get to evaluate the code using tool or guess the return value of f(x)?

[ Parent | on HN ]

Re:Large Language Models as Optimizers by sshh12 on Friday September 08, 2023 @03:23PM (#37438199)

Thanks! The LLM only sees the result of f(x). So like in the code writing example, the code is actually executed with `eval()`.

[ Parent | on HN ]