Lately my company has been doing a lot of complex accounting and reporting in spreadsheets. Overall was surprised by how well both GPT and Claude handled some of these extremely tedious tasks. Not uncommon to have an hours-long task compressed to minutes.
My anecdotal experience is GPT 5.2 Pro is decently ahead of Claude Opus 4.5 in this category when it gets to the tricky stuff, both in presentation and accuracy. The long reasoning seems to help a lot. But, apparently the benchmarks do not agree.
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.
Just a reminder that an accountant who might say "I use Currency format" is still working in binary floating point
as the format is just used as a display mask. And using VBA macros with the Currency type will hit problems at the boundary, when values move between the worksheet and the macro. The tool is broken in a way that proper accounting software is not...
Based on the article... is this basically just making Claude better at formatting and data presentation, or does it also get better at analysis? I get the impression it's the former.
And then you hand it to your boss who takes a 20 second look at it and asks why you made a projection that assume massive revenue growth and 3 years of perfectly flat utilities, insurance, G&A - no inflation etc.
It does look really promising as a skeleton starting point though. Like generate it, delete numbers and populate by hand.
Not unlike the boilerplate start we saw in AI coding a couple years back
You'll use a ton of AI but it won't wipe the humans out. In the end you'll have a compositional change, likely nothing catastrophic imo. In part because there is a buck to stop and Claude ain't got no hands...
> The side-by-side outputs below show how output quality has improved from Claude Opus 4.5 to Opus 4.6.
Disclaimer: I use AI to code (and I code for finance) and I love Anthropic.
But: for f-ck's sake, I cannot click on the picture and have it show up in full. It stays at its tiny size, impossible to read the numbers. I had to right-click and "open in a new tab".
AI is, somehow, definitely still not fully there yet.
Anthropic does anything to keep the Claude hype going; from fearmongering ("AI bad, need government regulations") to wishful thinking ("90% of code will be written by AI by the end of 2025" —Dario) to using Claude in applications it has no business being in (Cowork, accessing all your files, what could go wrong?) to releasing "research" papers every now and then to show how their AI "almost got out" and they stopped it (again, to show their models are "just that good") to prescribing what the society should do to adapt to the new reality to doing worthless surveys on "how AI is reshaping economy, but mostly our AI not others".
Lately my company has been doing a lot of complex accounting and reporting in spreadsheets. Overall was surprised by how well both GPT and Claude handled some of these extremely tedious tasks. Not uncommon to have an hours-long task compressed to minutes.
My anecdotal experience is GPT 5.2 Pro is decently ahead of Claude Opus 4.5 in this category when it gets to the tricky stuff, both in presentation and accuracy. The long reasoning seems to help a lot. But, apparently the benchmarks do not agree.
Edit - noticed OpenAI specifically focuses on finance use cases in their gpt-5.3-codex blog as well https://openai.com/index/introducing-gpt-5-3-codex/
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.
With tool use you do reduce the risks.
It's not like these models calculate.
I know plenty of nondeterministic accountants
Yeah, seriously, I use AI all day every day but that terrifies me.
Dont use Excel for accounting....
An Excel spreadsheet is a bad source of truth for data. It's fine for analytics though.
HN ignorance on display...
The Journal of Accountancy - "Bugged by Excel’s calculation errors" - https://www.journalofaccountancy.com/issues/2014/mar/excel-c...
ICAEW (Institute of Chartered Accountants) — "Rounding Errors Revisited" (Excel Tips #447) - https://www.icaew.com/technical/technology/excel-community/e...
Just a reminder that an accountant who might say "I use Currency format" is still working in binary floating point as the format is just used as a display mask. And using VBA macros with the Currency type will hit problems at the boundary, when values move between the worksheet and the macro. The tool is broken in a way that proper accounting software is not...
"Floating-point arithmetic may give inaccurate results in Excel" - https://learn.microsoft.com/en-us/troubleshoot/microsoft-365...
Based on the article... is this basically just making Claude better at formatting and data presentation, or does it also get better at analysis? I get the impression it's the former.
And then you hand it to your boss who takes a 20 second look at it and asks why you made a projection that assume massive revenue growth and 3 years of perfectly flat utilities, insurance, G&A - no inflation etc.
It does look really promising as a skeleton starting point though. Like generate it, delete numbers and populate by hand.
Not unlike the boilerplate start we saw in AI coding a couple years back
It's time to sell hedge fund stocks!! Jokes aside, I took the CFA exam last week and now I'm starting to worry about my career...
I wouldnt worry. Unless you are just memorising stuff and dont actually understand anything - then you should.
You'll use a ton of AI but it won't wipe the humans out. In the end you'll have a compositional change, likely nothing catastrophic imo. In part because there is a buck to stop and Claude ain't got no hands...
Article did not load on my tablet :sweat_smile:
> The side-by-side outputs below show how output quality has improved from Claude Opus 4.5 to Opus 4.6.
Disclaimer: I use AI to code (and I code for finance) and I love Anthropic.
But: for f-ck's sake, I cannot click on the picture and have it show up in full. It stays at its tiny size, impossible to read the numbers. I had to right-click and "open in a new tab".
AI is, somehow, definitely still not fully there yet.
Their chart only goes up to 70.
At least it starts at zero.
Anthropic does anything to keep the Claude hype going; from fearmongering ("AI bad, need government regulations") to wishful thinking ("90% of code will be written by AI by the end of 2025" —Dario) to using Claude in applications it has no business being in (Cowork, accessing all your files, what could go wrong?) to releasing "research" papers every now and then to show how their AI "almost got out" and they stopped it (again, to show their models are "just that good") to prescribing what the society should do to adapt to the new reality to doing worthless surveys on "how AI is reshaping economy, but mostly our AI not others".