Comment by qup
1 year ago
Are you sure it would be hard?
Maybe it only requires asking the LLM to be creative when designing the algorithm. The parent poster spent some time thinking about it, obviously--he didn't generate it accurately "on the fly," either. But he's able to direct his own attention.
I don't see why the LLM couldn't come up with this logic, if prompted to think about a clever algorithm that was highly specific to this problem.
I suspect that it would be unlikely to come up with it because it requires execution of a fairly lengthy algorithm (or sophisticated mathematical reasoning) to find the smallest/largest valid numbers in the range. You can verify this for yourself with the following ChatGPT prompt: "What is the smallest number in the range (1, 100000) whose digits sum to 30? Do not execute separate code."
O1 did find the optimization in a sibling comment (sibling to my GP)
So probably time to update your expectations
Why limit its ability to write separate code?
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.
4 replies →