[measurablefunc]

This is b/c these things are Markov chains. You can not expect consistent results & outputs.

[SrslyJosh]

Using an LLM for a "financial workflow" makes as much sense as integrating one with Excel. But who needs correct results when you're just working with money, right? ¯\_(ツ)_/¯

[mirekrusin]

Humans are non deterministic yet they use excel, work with financial workflows and deal with the money.

[thfuran]

And because one system that aims to achieve deterministic operation can’t quite perfectly do so, we might as well abandon any attempt at determinism?

[measurablefunc]

Computers are not humans & suggesting such equivalence reveals more than you realize.

[mirekrusin]

Do you mind to elaborate?

[Terr_]

"Humans make math errors, yet they do math anyway, therefore this calculator that makes errors is also OK."

What do you call the fallacy where the universe is imperfect, therefore nobody can have higher standards for anything?

Mankind has spent literal centuries observing deficiencies and faults in human bookkeeping and calculation, constantly trying to improve it with processes and machinery. There's no good reason to suddenly stop caring about those issues simply because the latest proposal is marketed as "AI".

[mirekrusin]

It can interact with deterministic and provable systems just fine.

[measurablefunc]

I think stochastic modeling can be useful but if that's not what they are aiming for then they are misunderstanding the technical limitations & would be better served by learning how their tools actually work instead of believing & trusting the corporate marketing from AI companies.

[ACCount37]

Did you actually read what the paper was about before leaving a low quality comment?

[measurablefunc]

Don't worry about the quality of my comments. Focus more on yours instead.