111–120 of 154 posts
it's how to account for bizarre ambiguous business situations often in the context of bureaucratic business requirements no LLM could currently create economically...
Earlier quoted context omitted.
Humans (accountants) are non-deterministic, so unsure if an LLM would be better or worse if we threw more effort at the problem. But in general, I tend to side with the "lets leave the math to purpose built models/applications" instead of generalized LLMS. LLMs are great if you are just aiming for "good enough to get through next quarter" type results. If you need 100% accuracy, an LLM isn't going to cut it.
Human accountants also have a very important property: liability. If a certified accountant told me to do X, I'm covered (at least to the point they would assist in recovering, or I can get compensation through their insurance). If LLM tells me, I'm in a bigger problem.
In my area (Vermont) the going rate for a good CPA is $200/hr. Bookkeepers are $20-30/hr.
Earlier quoted context omitted.
I'm sure that any accounting trick that an LLM can think of is something that is also used by some shady human accountants. The proper response should not be to avoid/prohibit AI but to improve the validation mechanisms.
No, I think in this particular case the proper response is for honest companies to avoid any systems which invent nonexistent transactions to reconcile books. Most businesses don’t want to misrepresent their books, irrespective of the existence of shady accountants.
Hey all, member of the benchmark team here! The goal for this project was to see how LLMs well could do bookkeeping without an overly opinionated scaffold. We gave them access to processed transaction records and code execution tools, but it was up to them to choose exactly how to use those. Claude and Grok 4 did reasonably well (within CPA baselines) for the first few months, but tended to degrade as more data came…
It's a start. The world needs a better way to handle bookkeeping, and the existing tools sure aren't cutting it. Bookkeeping for my small business runs into the tens of thousands of dollars every year, and the amount of human error associated with processing assorted ecommerce and other transactions is astounding, even after extensive planning and SOPs. The other pain point is Quickbooks. The tool is so sprawling and…
But can't it, literally, hallucinate raw data at any point in the run?
Earlier quoted context omitted.
Humans (accountants) are non-deterministic, so unsure if an LLM would be better or worse if we threw more effort at the problem. But in general, I tend to side with the "lets leave the math to purpose built models/applications" instead of generalized LLMS. LLMs are great if you are just aiming for "good enough to get through next quarter" type results. If you need 100% accuracy, an LLM isn't going to cut it.
Human accountants also have a very important property: liability. If a certified accountant told me to do X, I'm covered (at least to the point they would assist in recovering, or I can get compensation through their insurance). If LLM tells me, I'm in a bigger problem.
Earlier quoted context omitted.
No, I think in this particular case the proper response is for honest companies to avoid any systems which invent nonexistent transactions to reconcile books. Most businesses don’t want to misrepresent their books, irrespective of the existence of shady accountants.
It is really really common for book keepers to create transactions to reconcile books. Not okay, but ‘journal entries’ are pervasive.
Earlier quoted context omitted.
If the "extremely precise requirements" can be cheaply and automatically validated, it's much easier to have the AI generate spam on a loop until it passes all the tests.
You're saying P=NP, I think.
They’re not really making any claims about how quickly the AI can solve relative to the validation, which is what P vs NP is about.