Because otherwise we are talking about LLMs augmented with external tools (i.e. Python interpreters). My original comment was pointing to the limitations of LLMs in writing code by themselves.
You wouldn't ask a programmer to solve a problem and then also not let them write down the source or debug the program as you write it?
Are you asking it to not write down an algorithm that is general? They are doing a pretty good job on mathematical proofs.
I still don't understand why you wouldn't let its full reasoning abilities by letting it write down code or even another agent. We should be testing towards the result not the methods.
I'm simply pointing out the limitations of LLMs as code writers. Hybrid systems like ChatGPT-o1 that augment LLMs with tools like Python interpreters certainly have the potential to improve their performance. I am in full agreement!
It is worth noting that even ChatGPT-o1 doesn't seem capable of finding this code optimization, despite having access to a Python interpreter.
But programmers are LLMs augmented with the ability to run code. It seems odd to add a restriction when testing if an LLM is "as good as" a programmer, because if the LLM knows what it would need to do with the external code, that's just as good.
