Only if you treat the generated code (and the costs; time and money, even if infinitesimal) as non-disposable.
One can (and probably should) make the argument that if your initial/incremental belief was incorrect, one should start again with a fresh prompt or roll back the tree and prompt again, disposing of the now-incorrectly generated code.
I catch myself doing this all the time. My model (local) isn't nearly as fast as something cloud-based, so there is a real incurred cost of time that is hard to shake. Very often I'll need the model to reconsider and rewrite the plan after it's already done quite a bit of work. Rolling back the code is tough, but I should resort to it more often.
Yes. My thought is that the OP title is 100% opposite of the truth: Dealing with LLMs quickly teaches you to mercilessly throw work away and start from a clean slate lightly.
3 comments
[ 3.7 ms ] story [ 14.8 ms ] threadOne can (and probably should) make the argument that if your initial/incremental belief was incorrect, one should start again with a fresh prompt or roll back the tree and prompt again, disposing of the now-incorrectly generated code.
I catch myself doing this all the time. My model (local) isn't nearly as fast as something cloud-based, so there is a real incurred cost of time that is hard to shake. Very often I'll need the model to reconsider and rewrite the plan after it's already done quite a bit of work. Rolling back the code is tough, but I should resort to it more often.
Obviously not as nimble as changing your own thoughts mid-sentence but drastically better than waiting for the full output first.