Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GLM 5.2 is nearly as accurate as a human book keeper

toot-books.com

Post reply on HN
Print view View original

81–90 of 131 posts

Re: GLM 5.2 is nearly as accurate as a human book keeper

#81

Post by petesergeant »

Shitty-kitty wrote: post #52
petesergeant wrote: post #9

Oh, I'm actively doing this at the moment. FreeAgent grabs my transactions from Wise already, and then I give it [Claude Code, in fact] a folder of PDFs to attach to my invoices, including figuring out VAT, and it's uploading what it found using the FreeAgent API. My accountant hasn't complained yet, and it seems considerably more accurate than when my wife was doing it. Quiet plug for https://github.com/pjlsergeant/…

The problem with LLM's is that they could work correctly for months and years and then do something egregious which will will go unnoticed because of the misplaced trust one develops on a system that "just seems to work." Get flagged for an expensive audit and there go all the savings and then some.

isn't that true for humans too?

Re: GLM 5.2 is nearly as accurate as a human book keeper

#82

Post by sublinear »

paytonjjones wrote: post #76
sublinear wrote: post #43

Earlier quoted context omitted.

AI helps automate things that didn't already have rigorous formatting and structures available as input... and that's really all it does (99% of the time). Doesn't matter how many more nines you add, rigorous formatting is still required . In some cases, it has teeth with compliance standards. Those standards cannot be compromised because there are already a lot of other layers contributing inaccuracy. It all adds up…

> doesn't matter how many more nines you add I don't get this argument. People say the same about autonomous driving. But humans also have some number of nines. If you can get it better than humans, that's better!

Manual data entry and other tedious chores are definitely unreliable. However, running a script that a human wrote according to committee specs is the most reliable part. You're conflating the different aspects of human work. We are much better at understanding our needs and arguing about them than doing the manual part.

So, I don't get your argument either. I hear yours often enough and so much louder that I feel it's a deliberate muddying of waters.

What cannot be obsoleted by automation becomes bureaucracy. To my ears, it sounds like you're afraid of ending the tech wild west. That bureaucracy was always the most valuable part, and the demand for experienced programmers over at that table is very high.

Re: GLM 5.2 is nearly as accurate as a human book keeper

#83

Post by giancarlostoro »

ivababukova wrote: post #40
giancarlostoro wrote: post #36

Earlier quoted context omitted.

What if the model misses something entirely, so it's not in the review? ;)

It is given a list of transactions as an input. If it misses one or more of them, that will be noticeable immediately. In the VAT return, one can see if something is missing very easily if the numbers do not align.

At some point I feel like you're better off making the model build a tool to scrape all the values...

Re: GLM 5.2 is nearly as accurate as a human book keeper

#84

Post by limaoscarjuliet »

ofjcihen wrote: post #48
Diogenesian wrote: post #31

This shouldn't be ignored in the discussion here: The job performed by the humans was broader than what was requested of the model in this benchmark: humans also had to find the relevant invoices (searching through mailboxes, or requesting them from providers) and reason through any circumstances which cannot be inferred from the bank feed and invoices/receipts on their own. In the benchmark these circumstances are p…

Hahaha non-deterministic accounting probably won’t fly well with the IRS

The "beatings" delivered by IRS will be deterministic for sure!

Re: GLM 5.2 is nearly as accurate as a human book keeper

#85

Post by walrus01 »

mediaman wrote: post #79
walrus01 wrote: post #74

Earlier quoted context omitted.

Indeed so, a fairly mundane RFP, RFQ, buyer, receiver, accounts payable process will stop a lot of problems. If an agent is inserted at some stage in the process with a clear path to make a ticket/escalate to a human if it sees something it doesn't understand, the risk isn't absurdly high , in my opinion. I've seen so many reports of humans with the authority/ability to execute an outgoing SWIFT transfer who've been…

I have seen the SWIFT thing happen for $100k. I think AI could actually be better for this, because it's often easier to implement hard rules for the AI. With the SWIFT incident I saw, there was a rule that no payment can go to a vendor's bank that isn't a current, approved vendor. But the rule was not enforced in software: it was an internal accounting rule that humans were supposed to follow. The AP person "thought…

Another thing that seems to be disturbingly common these days is some party involved in residential real estate transactions having a RAT on one or more PCs, and/or compromised email account, intercepting an email at the closing stages of a house purchase and sending someone information to send a wire transfer to a fraudulent location.

Re: GLM 5.2 is nearly as accurate as a human book keeper

#86

Post by rustcleaner »

__MatrixMan__ wrote: post #64

I'm not so interested in having an LLM do my bookkeeping for me. But I'm very interested in whether LLM's can unravel the accounting obfuscations that billionaires use to avoid paying taxes on their wealth.

One idea I've had for reform is to ban central banks from inventing new currency except to pay every citizen a UBI debt free, and only tax limited liability entities (not humans). This would give citizens, instead of borrowers, first spend on new money and orient limited liability entities to serving citizens in the market to get their taxed revenues. It would also be a boon for financial privacy and reduce the burden on the average man.

Re: GLM 5.2 is nearly as accurate as a human book keeper

#87

Post by rustcleaner »

lowsong wrote: post #46

That "nearly" is doing an awful lot of heavy lifting. It doesn't matter if your AI model is 99% or 99.99% accurate. For a tax return it has to be perfect every time or someone is at best getting a fine or at worst going to prison. Sure, human error happens too, but humans take accountability. That's why accountants are a regulated profession. Until an AI company CEO is willing to go prison if the output of their mode…

What about errors resulting in overpaying taxes?

Re: GLM 5.2 is nearly as accurate as a human book keeper

#88

Post by quickthrowman »

Obscurity4340 wrote: post #21
cs702 wrote: post #17

It's not hard to imagine that will be able to do as good a job as a human accountant in the not too distant future. It's also not hard to imagine tax authorities using AI to audit everyone's tax returns every year. We sure live in interesting times.

The real test to see if AI is just a rich person thing will be to see how the tax authorities treat it, even for more complex returns. They can save humans for the really complex edge case stuff but at the end of the day, the tax code is just checkboxes and input forms that get boiled down into Integers, Floats/Doubles and enumerated choices with some Strings for deductions

Bookkeeping is not tax preparation, just FYI. The reports generated by an accounting system are used on tax returns for companies, but they’re distinctly different things.

Re: GLM 5.2 is nearly as accurate as a human book keeper

#89

Post by fibers »

josefritzishere wrote: post #72

I can't file "almost" with the IRS. That's not going to end well. Sorry Mr. auditor, this is a non-deterministic filing.

thats not true. maybe for simple 1040s yes, but depending on what you have you could take aggressive positions bc they could be subject to valuation differences.

Re: GLM 5.2 is nearly as accurate as a human book keeper

#90

Post by ofjcihen »

ACCount37 wrote: post #58
ofjcihen wrote: post #48

Earlier quoted context omitted.

Hahaha non-deterministic accounting probably won’t fly well with the IRS

Do you think human accountants are deterministic? Get a large enough org and watch your accounting grow an error margin.

Ha even if this was true (it’s not) you’re basically saying “humans will make some mistakes so let’s throw caution to the wind” which is probably the worst application of AI that I’ve heard yet.
Post reply on HN