I feel like I'd be really skeptical of results from a non-deterministic model for something as precise as accounting....

The deterministic part (calculations) is done by Excel.

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.

"The non-deterministic part is turning human instructions ("calculate the NPV over 10 years for X given Y") into Excel."

erm theres an NPV function built in excel.

> erm theres an NPV function built in excel.

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.

But humans non-deterministically use that or use a hand-rolled formula.

[dead]

I know plenty of nondeterministic accountants

With tool use you do reduce the risks.

It's not like these models calculate.

Yeah, seriously, I use AI all day every day but that terrifies me.