ChatGPT for Excel (chatgpt.com)

by armcat 198 comments 341 points
Read article View on HN

198 comments

[−] strongpigeon 29d ago
Oh wow, I used to work on Excel Add-Ins about 10 years ago. Even got a patent for it. I'd be curious to see how they implemented the calls.

We came up with what I still consider a pretty cool batch-rpc mechanism under the hood so that you wouldn't have to cross the process boundary on every OM calls (which is especially costly on Excel Web). I remember fighting so hard to have it be called context.sync() instead of context.executeAsync()...

That being said, done poorly it can be slow as the round-trip time on web can be on the order of seconds (at least back then).

[−] Acmeon 29d ago
Do you mean that you worked on the Excel Add-Ins platform in Excel (and not on a specific Add-In)?

If you were working on the platform itself, then I would be interested in hearing your more detailed thoughts on the matters you mentioned (especially since I am developing an open source Excel Add-In Webcellar (https://github.com/Acmeon/Webcellar)).

What do you mean with a "OM" call? And why are they especially costly on Excel web (currently my add-in is only developed for desktop Excel, but I might consider adding support for Excel web in the future)?

In any case, context.sync() is much better than context.executeAsync().

[−] strongpigeon 29d ago
I worked on the Excel Add-Ins platform at Microsoft, yes. By OM call I mean "Object Model" call, basically interacting with the Excel document.

The reason those calls are expensive on Excel Web is that you're running your add-in in the browser, so every .sync() call has to go all the way to the server and back in order to see any changes. If you're doing those calls in a loop, you're looking at 500ms to 2-3s latency for every call (that was back then, it might be better now). On the desktop app it's not as bad since the add-in and the Excel process are on the same machine so what you're paying is mostly serialization costs.

Happy to answer more questions, though I left MSFT in 2017 so some things might have changed since.

[−] com2kid 29d ago
Does Excel for Web still spin up an actual copy of Excel.exe on a machine somewhere? I heard that is how the initial version worked.
[−] strongpigeon 29d ago
No, as the other comment mentioned. But I’ve heard of more than a few customers running their own “server excel workflow” where they have an instances of excel.exe running a VBA macro that talks to a web server (and does some processing).
[−] p_ing 29d ago
Never did this. WAC was the original version (integrated with SharePoint Server). Everything was server-side.
[−] Acmeon 29d ago
Yeah, that makes sense. For some reason, I was under the impression that all calculations run locally in the browser, which would have been comparable to how Excel desktop works (i.e., local calculations). Is there a reason for why the Excel calculations run on the server (e.g., excessive workload of a browser implementation, proprietary code, difficult to implement in JavaScript, cross browser compatibility issues, etc.)? Furthermore, if the reason for this architecture is (or was) limitations in JavaScript or browsers, do you find it plausible that the Excel calculations will some day be implemented in Webassembly?

Regardless, I have always preferred Excel desktop over Excel web (and other web based spreadsheet alternatives). This information makes me somewhat less interested in Excel web. Nonetheless, I find Excel Add-Ins useful, primarily because they bring the capabilities of JavaScript to Excel.

[−] DaiPlusPlus 29d ago

> though I left MSFT in 2017 so some things might have changed since.

Honestly, I struggle to think about what has actually changed between Office 2013 and Office 2024 (and their Office 365 equivalents); I know the LAMBDA function was a big deal, but they made the UI objectively worse by wasting screen-space with ever-increasingly phatter non-touch UI elements; and the Python announcement was huge... before deflating like a popped party balloon when we learned how horribly compromised it was.

...but other than that, Excel remains exactly as frustrating to use for even simple tasks - like parsing a date string - today just as it was 15 years ago[1].

[1]: https://stackoverflow.com/questions/4896116/parsing-an-iso86...

[−] lateforwork 29d ago
This looks bad for Microsoft. They added a Copilot button to all their products but it doesn't do much more than open a chat side panel.

I recently tried Claude Cowork for PowerPoint and I was stunned by the content as well as design quality of the deck it produced. That's a threat for Microsoft because now you don't need the editing tools of PowerPoint, AI replaces it, so all you need is the presentation mode of PowerPoint.

Copilot for Excel is useless. Ask it what is in cell A1 and it can't answer. I am looking forward to trying ChatGPT for Excel.

[−] angadsg 29d ago
Hi everyone, engineer on ChatGPT for Excel here - we launched ChatGPT for Excel to bring the power of GPT-5.4 to Excel. Keen to hear feedback and happy to answer any questions!
[−] arjie 29d ago
I’ve always found it unbelievable how bad Gemini’s Google Sheets interaction is. Copying the sheets into Claude and then modifying them there and copying them back actually outperforms it.

Nowadays I just make single-purpose websites with Claude Code because Google Sheets has such poor AI integration and is outrageously tedious to edit.

They had all the parts and I have a subscription and it still does terrible things like prompt me to use pandas after exporting as a CSV. It will mention some cell and then can’t read it. It can’t edit tables so they just get overwritten with other tables it generates.

It reminds me of something a friend told me: he heard that Google employees do dogfood their products; some even multiple times every year. There’s no way anyone internal uses Sheets even that often.

[−] TrackerFF 29d ago
I've experimented with ChatGPT for spreadsheets the past 6 months, and while the results look nice now it has been excruciatingly slow for even the simplest spreadsheet. I'm talking 15-20 minutes to make some pretty basic calculator with graphs. IIRC, it used a lot of time purely on the styling.
[−] Acmeon 29d ago
In principle, I find it valuable to integrate tools. However, in this case I would be somewhat cautious, especially as "your chats, attachments, and workbook content — may be shared with OpenAI" (as per the Microsoft Marketplace description: https://marketplace.microsoft.com/en-us/product/WA200010215?...).

This seems like a security nightmare, which is especially relevant because sensitive data is often stored in Excel files.

[−] flybrand 29d ago
Several months ago, ChatGPT swore to me it had interoperability with both excel and Google Sheets. I spent 90 minutes thinking I was an idiot, trying to follow its guidance before asking the internet.
[−] w2df 29d ago
Copying Anthropic again lol.

Damn that OAI valuation is like a sore boil that is about to explode.

Also once again, a lack of imagination from OAI. Damn vision really is super scarce huh.

[−] tills13 29d ago
These AI in Excel products are a financial crisis waiting to happen. Or maybe just Enron but stupider.
[−] HerbManic 29d ago
It was partially a joke but someone posted a image of Co-pilot in Excel to demonstrate the limits of these things. Three cells with three numbers (1, 2, 3) and co-pilot asked to sum these three up.

Instead of answering with 6, it came up with 15. The comment was "If AI is doing this, a global financial crash is inevitable."

Might not be real but it is something to keep an eye on. Hopefully, they are a bit more cautious on how this is implemented.

[−] TacticalCoder 29d ago
Speaking of which... The corporate world, which was already, since forever, producing Powerpoint presentations containing bogus numbers from buggy spreadsheet (I've been tasked once to port a corporate spreadsheet to a dedicated internal app and I then understood decisions in the world were taken, everywhere, based on bogus numbers from broken reports made by spreadsheets full of broken numbers/assumptions) is now going full-speed ahead: many vendors have added "Artificial 'Intelligence'" to their corporate tools and...

There are now just even more errors than there already were.

Now there's hope though: I take it at some point, just like we have AI that can already find (and fix and sometimes even properly fix) errors in code, we may end up with AI tools able to find all the broken assumptions and errors / wrong formulas the spreadsheets that make the corporate world are full of. But atm that's not where we are.

One such corporate-world company producing a gigantic turd would the "biggest" (but it's really not that big) european software company, SAP... They're going full on "business AI" as they see (rightly so?) AI as a terminal death threat to their revenue model. Market cap went from $360 bn to $200 bn: don't know if it's related to their "genius" AI-move.

And so now we have countless corporate drones who were already incapable of doing any kind of financial/accounting/math computation in a rigorous way who are now double-speeding on the errors, but this time AI-augmented.

It's the "let's add an AI chatbot to our site" (which so many companies are adding to their websites right now), but corporate version: "let's add AI to our corporate tools".

Just to be clear: I think this cannot fail. Failure and bogus numbers are the norm in spreadsheets, not the exception. More failure, more bogus computations, actually won't change a thing.

[−] p_ing 29d ago
Microsoft has this built-in using Claude models (for M365 Copilot licensed users). I don't know why you'd use this as an M365 subscriber in an enterprise. I'm sure there's some edge cases, but MSFT has been moving away from OAI. Even Copilot Studio agents now default to Sonnet 4.6 and not GPT 5.
[−] tboughen 28d ago
I am a ChatGPT plus user in the UK. I believe this should work for me as I am outside the EU (!), but every time I have tried it I get ‘Currently Unavailable - please try again later’. Which is very unhelpful.
[−] thih9 29d ago

> Follow along so you can trust the work

> (…) you can verify each step and revert edits if needed.

I wish there were different workflows.

It feels like current most popular way of working with GenAI requires the operator to perform significant QA. The net time savings are usually positive. But it still feels inefficient, risky and frustrating, especially with more complex and/or niche problem areas.

Are there GenAI products that focus more on skill enhancement than replacement? Or any other workflows that improve reliability?

[−] mritchie712 29d ago
I remembered this post from (only) 3 years ago:

Show HN: I've built a C# IDE, Runtime, and AppStore inside Excel

670 points | 179 comments

One of the main use cases was to analyze Excel data with SQL. I'm the kind of nerd that loves stuff like that, but stuff like that seems completely obsolete now.

[0] https://news.ycombinator.com/item?id=34516366