I feel like I'd be really skeptical of results from a non-deterministic model for something as precise as accounting....
The non-deterministic part is turning human instructions ("calculate the NPV over 10 years for X given Y") into Excel.
This is already a non-deterministic process (humans are non-deterministic!). The question is if an AI model can be more reliable than humans, and I can't see any reason why it wouldn't be.
The correct path is pretty clear, so the logits for following that path are going to be a long way from off-path.
For something like this the real problem is training the model to use Excel (which will show up by it being confused which sheet it is on or trying to use the wrong window or things like that), not the non-determinism.
erm theres an NPV function built in excel.
Have you ever done anything related to corp finance/valuation in a professional setting? Highly doubt it.
Exactly!
The LLM just needs to make sure it uses it appropriately. Doing that bit is the non-deterministic part, but the NPV calculation itself is completely deterministic.
This process of deciding what data to put in what column and how to apply NPV to it is non-deterministic. You could choose to put it in column A, or column B or maybe even row 3 - it depends!
The LLM does that part non-deterministically.
Yet I don't understand the aha moment here? It might save analyst time but aren't there already enough automation that you don't really need to tell the AI to tell the math-doing-thing to do the math because the math-doing-thing is already optimized for most general functions? What are we gaining from adding the non-deterministic process here when the real non-deterministic process is still the human being prompting what to do?
Seems like a solution to a non-problem from my pov.
And it has all the requirement translation requirements of programming
It's not like these models calculate.