[HN Gopher] ChatGPT for Excel
       ___________________________________________________________________
        
       ChatGPT for Excel
        
       Author : armcat
       Score  : 317 points
       Date   : 2026-04-15 21:21 UTC (1 days ago)
        
 (HTM) web link (chatgpt.com)
 (TXT) w3m dump (chatgpt.com)
        
       | haneul wrote:
       | Except for pro and plus users in the EU eh...
        
       | flybrand wrote:
       | 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.
        
       | lateforwork wrote:
       | 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.
        
         | screye wrote:
         | If AI winning means that data center companies win out, then
         | the wins for Azure will more than make up for the death of
         | Office.
         | 
         | I am surprised that Microsoft's own copilot product is so far
         | behind though.
        
           | boringg wrote:
           | Aren't they providing a wrapper for the work of another
           | company? IE msft isn't actually doing any foundational work
           | thus they can't meaningfully move product capability, just
           | wait for the model to improve and integrate it?
        
         | bwat49 wrote:
         | its baffling how badly microsoft has handled copilot, this is
         | exactly what copilot in office should have been
        
         | miohtama wrote:
         | It's called Microslop for a reason.
        
         | ebbi wrote:
         | We have many people in my wider team (Finance) that are AI
         | skeptics purely because of their experience with Copilot. Like
         | they don't know what AI is actually capable of when outside of
         | the shackles of Copilot.
         | 
         | Microsoft fumbled so badly here.
        
         | evanjrowley wrote:
         | There is a significant difference in experience between Copilot
         | Basic for a M365 user whose IT admins have blocked integration
         | capabilities with Sharepoint content vs Copilot Premium for a
         | M365 user whose IT admins have allowed integration capabilities
         | with Sharepoint content.
        
           | interroboink wrote:
           | A recent funny story on this topic:
           | https://idiallo.com/blog/what-is-copilot-exactly
           | 
           | HN discussion: https://news.ycombinator.com/item?id=47603231
        
           | mohamedkoubaa wrote:
           | Microsoft is better off not allowing copilot basic because of
           | the reputational harm it will do. Not that they are thinking
           | through copilot rationally
        
             | basch wrote:
             | it was a good name when chosen. too bad they have burned
             | bob, clippy, cortana, sydney, and copilot already.
        
               | alternatex wrote:
               | The backend of Copilot is still called Sydney AFAIK
        
               | compass_copium wrote:
               | Don't forget Tay!
        
         | Handy-Man wrote:
         | You have to use the "agent" toggle for Copilot to behave the
         | same way lol. Otherwise its pretty simple chat interface with
         | the context, that's all.
        
         | LuxBennu wrote:
         | Chatgpt for Excel is still an office add-in running in the same
         | sandbox though. strongpigeon described the exact bottleneck
         | upthread, process boundary crossings, context.sync() roundtrips
         | that take seconds on web. That's a platform limitation, not a
         | model limitation. Swapping AI behind the add-in doesn't fix the
         | fundamental constraint that third-party add-ins can't deeply
         | integrate with Excel's runtime the way a native feature can. If
         | copilot is bad despite having more access to excel internals(I
         | don't like how Copilot is designed or implemented tho), an add-
         | in with less access is likely not be better.
        
           | com2kid wrote:
           | There is an irony here that this would be more performant
           | with a 2002 coding model. A native plugin, COM, OLE,
           | whatever. C++, crash prone, but fast.
        
             | strongpigeon wrote:
             | Maybe but not drastically so. My guess is that most of the
             | slowness comes from the tool calls round
             | tripping+processing on Anthropic/OpenAI's servers rather
             | than the app latency.
             | 
             | That's without talking about the poor UI and security story
             | of COM add-ins and the inability to run on Excel for iOS.
        
           | angadsg wrote:
           | Would love for you to try both copilot and ChatGPT for Excel.
           | Agreed on the limitations - but in our experience, ChatGPT
           | for Excel does really well on complex sheets.
        
         | nsiemsen wrote:
         | Claude for excel is already amazing. Fully capable of doing
         | junior work. Formatting is great. Can refactor large multi-tab
         | spreadsheets. It just burns tokens. If OpenAI is going to
         | subsidize this on the monthly enterprise plans for a while then
         | it's a game changer.
         | 
         | Claude for Excel (I work in finance) was one of the absolutely
         | critical reasons we added Anthropic enterprise licenses. But
         | they've turned out to be quite expensive ($100/day for heavy
         | users). We'll see what OpenAI's quotas are.
        
           | p_ing wrote:
           | Cheaper to get M365 Copilot licenses for the Claude models in
           | Excel.
        
             | WillAdams wrote:
             | What are the costs on that?
             | 
             | Does this remove (or at least increase) the upload limit?
        
               | p_ing wrote:
               | $200-something per user per year. Will vary based on
               | license type and seat count.
               | 
               | No limits.
        
               | croes wrote:
               | > No limits.
               | 
               | Yet.
        
               | codeugo wrote:
               | lol
        
               | mastermage wrote:
               | Well other than the limits of Copilots usefullness.
        
             | jxmesth wrote:
             | I tried looking this up but wasn't able to find info on
             | this on Microsoft's website. Do you have a link for this?
        
               | p_ing wrote:
               | https://support.microsoft.com/en-us/topic/choose-your-
               | model-...
        
           | intended wrote:
           | How's that been in practice ? From what I've been following -
           | Claude in finance results in models with errors that an
           | analyst won't make.
           | 
           | You get models that are formatted and structured and which
           | balance - but there are errors introduced which an analyst /
           | human wouldn't make.
           | 
           | Stuff like hard coded values, or incorrect cell logic which
           | guarantees the model balances.
        
             | mukmuk wrote:
             | From my experience, LLM performance in these areas is being
             | massively oversold. I have repeatedly tried using Claude to
             | modify a range of models typical of investment banking /
             | private equity / sellside research contexts, and the
             | results have been generally disastrous. On multiple
             | occasions, the xlsx would no longer open.
        
             | balderdash wrote:
             | Just my experience, it's not a solution but rather a
             | productivity tool. I mostly use it for tasks I can do
             | myself but it would probably take 20-30min to dial in - now
             | Claude can do it in 2-3min. (E.g. in a data table - add a
             | new column that checks column a if the data is a, do x, if
             | the data is b, do y, if the data is c, do z - then combine
             | that with the word after the hyphen in column b --- or
             | another example --- create a new sheet that is the same
             | format as sheet one but show calculates the difference
             | between column a and b bot for sheets 1-12 in a summary)
             | 
             | I don't get good results when I just have Claude build
             | things on its own - but for these types of specific
             | productivity tasks I can save a couple of hours here and
             | there.
        
           | wouldbecouldbe wrote:
           | I work with large files a lot, running claude code on it is
           | not token intense at all. Probably because it does a lot with
           | scripts. But its a bit more raw, but i think in the end more
           | powerful. Have to pick a good excel library and language. I
           | do node, maybe python can work as well
        
           | infecto wrote:
           | Work in a firm similar to yours and we have been going to
           | though the motions of figuring ways for the bullpen to make
           | use of these tools and would love to hear your thoughts if
           | you would be willing to share!
        
         | d3Xt3r wrote:
         | > 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.
         | 
         | Actually, someone here posted a Claude Code skill recently that
         | generates a presentation as a self-contained HTML5 file, so all
         | you need is a browser.
         | 
         | PowerPoint, as a whole, is doomed.
        
           | jason_zig wrote:
           | I'm not sure that's true - try getting someone to pull up an
           | html5 file on their computer for a presentation...
        
             | raincole wrote:
             | You mean like, double-click?
        
               | apsurd wrote:
               | you must never have actually done this. it doesn't work
               | the way you think it does. unless it's self contained
               | (like a pp), you can't expect network access to actually
               | deliver when you need it most.
        
               | d3Xt3r wrote:
               | The file the Claude skill spits out is actually fully
               | self-contained, no network access is needed.
        
               | apsurd wrote:
               | that's pretty cool!
        
             | DrSAR wrote:
             | hrm, double-click and your browser does the rest.
             | 
             | For added benefit, full screen?
             | 
             | Until you need presenter notes or other niceties, this
             | covers a large space of usage.
        
           | apsurd wrote:
           | you could do that for the past 20 years. i've always hated
           | slides as a medium for _anything_ , but i've been proven
           | wrong tine and again that people love their pp.
        
             | bad_haircut72 wrote:
             | Because it was drag and drop interface. This existed for
             | HTML but because web pages got too complicated, so did the
             | WYSIWYGs. By just being a program to show slides, the
             | editing experience was manageable for anyone. But if you
             | can hust type what you want to happen into claude, editng
             | experience doesnt matter as much/at all
        
           | basch wrote:
           | Or you could just talk to powerpoint, which creates a self
           | contained pptx, which also plays anywhere.
           | 
           | we've hit this point where its cool to have claude reinvent
           | every wheel just because it can.
        
             | d3Xt3r wrote:
             | It's not self-contained, it requires PowerPoint to be
             | indfled. Which is not an issue on corporate machines of
             | course, but maybe you want to do a presentation for a
             | general/broader audience.
        
               | alternatex wrote:
               | Office, or rather Microsoft 365 applications have had web
               | versions for a decade now.
        
               | d3Xt3r wrote:
               | That's besides the point though. With a self-contained
               | HTML, you don't need to go to a special website, you
               | don't need an account or sign-in, heck you don't even
               | need the Internet, and it works pretty much on every
               | device that supports HTML5.
        
           | hgoel wrote:
           | Powerpoint will continue to persist because other people need
           | to be able to edit your slide deck without understanding your
           | HTML.
           | 
           | My employer blocks office plugins, so I can't try Claude for
           | PowerPoint, but sometimes I get Claude to generate Python
           | scripts, which produce PowerPoint slides via python-pptx.
           | This also benefits from being able to easily read and
           | generate figures from raw data.
           | 
           | I don't really like the way Claude tends to format slides
           | (too much marketing speak and flowcharts), but it has good
           | ideas often enough that it's still worth it to me. So I treat
           | this as a starting point and replace the bad parts.
        
           | usrme wrote:
           | I'd love to get a link to that comment/post!
        
             | d3Xt3r wrote:
             | https://github.com/shawnzam/keynot
        
         | vessenes wrote:
         | Microsoft has rights to all this IP. So, it might look bad for
         | their product folks, but for the corporation this is great, to
         | the extent it works.
        
         | vipipiccf wrote:
         | I've had the same experience. Copilot for Excel can't even
         | parse basic cell references. Meanwhile Claude handles document
         | formatting in one pass. The catch is it works externally, not
         | inside the app, but at least it works.
         | 
         | The MCP ecosystem is what makes this interesting. Claude isn't
         | just a chat panel bolted onto existing software, it's building
         | integrations that actually manipulate the files. Microsoft had
         | the distribution advantage but they're losing on capability.
        
           | chris_money202 wrote:
           | stride.microsoft.com -> microsoft has this stuff you just
           | don't know it unless you are an M365 power user
        
             | compass_copium wrote:
             | I would consider myself an M365 power user and I was not
             | aware of this. It is not well promoted--and after all the
             | Copilot crap, I would be annoyed even if it was.
             | 
             | Regardless, I just tried to log in with my work MS account,
             | and I can't do so.
        
               | chris_money202 wrote:
               | Enterprise is Copilot Cowork one of the frontier agents.
               | Has to be enabled by your organization I believe
        
         | Gareth321 wrote:
         | > They added a Copilot button to all their products but it
         | doesn't do much more than open a chat side panel.
         | 
         | I was hyped when I heard about Copilot. "I can tell it to make
         | pivot tables now!" When I tried to use it I was shocked how
         | underbaked it was. Below even my worst expectations. This
         | really was someone shoving ChatGPT into Excel with almost zero
         | additional effort. Copilot can't DO anything useful.
        
           | chris_money202 wrote:
           | stride.microsoft.com -> this is a virtual machine instance
           | with developer tools that allow for same sort of work Claude
           | cowork does. Copilot in excel has to access the excel
           | document through excel provided APIs and can't completely
           | redo the document like cowork does everytime running
           | developer scripts to generate it because the document
           | instance is open. The model of work is entirely different.
        
         | sarreph wrote:
         | > This looks bad for Microsoft.
         | 
         | Maybe(?) from a product catalogue perspective... But from a
         | strategic perspective less so because they own ~27% of
         | OpenAI.[0]
         | 
         | [0] - https://openai.com/index/next-chapter-of-microsoft-
         | openai-pa...
        
         | ryanjshaw wrote:
         | There's a magic button you have to press to make it integrate
         | fully. Everybody is confused about why this isn't the default
         | behavior.
        
         | chris_money202 wrote:
         | stride.microsoft.com is the cowork equivalent I believe.
        
           | p_ing wrote:
           | Only for personal accounts. Enterprise customers have a
           | Frontier agent called Copilot Cowork via the M365 Copilot
           | app.... copilot.
        
         | xeyownt wrote:
         | it would be bad for Microsoft if that would use Calc on
         | LibreOffice.
        
         | giancarlostoro wrote:
         | I am still surprised that outside of open source AI models,
         | Microsoft is just routing to external models, to a degree its
         | kind of smart because they don't have to have all the skin in
         | the game for the infrastructure, plus they sell some of the
         | hosting anyway, but man. Why does Microsoft not have a frontier
         | model yet? Would have been a great time any time in the last
         | few years to introduce a real Cortana AI model.
        
           | ebiester wrote:
           | They explicitly said they were ceding the frontier model game
           | to others, and that they were content saying a few months
           | behind the state of the art. In the long run, this is an
           | interesting freeloader play that a few people are making.
           | https://www.cnbc.com/2025/04/04/microsoft-ai-chief-sees-
           | bene...
        
           | leetharris wrote:
           | I will say this in the most charitable terms I can. Microsoft
           | simply does not have it in their culture to compete with
           | something like this. Their prime days are over. They are
           | slowly becoming IBM.
           | 
           | They were completely correct to not compete in foundation
           | models. They would have no chance. I mean, they can't even
           | make a decent app or harness to use the other models!
        
         | brookst wrote:
         | PowerPoint is the poster child for the class of applications
         | that AI totally obsoletes:
         | 
         | * A large application whose outputs are independent of the all
         | (people still print slides; when presenting nobody knows or
         | cares what app was used) * Complicated and requires users to
         | learn lots of skills unrelated to the work they're doing
         | (compare to Excel, where the model and calculations require and
         | reflect domain knowledge about the data) * Practically zero
         | value add in document / info management (compare to word where
         | large documents benefit from structure and organization)
         | 
         | We're pretty close to presentations just being image files
         | without layers and objects and smartart and all that.
         | 
         | AI will come for all productivity tools, but PowerPoint will be
         | the canary that gets snuffed first, and soon.
        
         | bko wrote:
         | Maybe a dumb question, but why does Microsoft care? They should
         | have good apps and if OpenAI or Claude wants to create plugins,
         | great. That's what they're there for and Microsoft invested a
         | lot of effort to make the new add-ins much more powerful and
         | intuitive for this very reason. It's really nice experience
         | compared to VBA.
         | 
         | It obv makes Excel much more valuable and they can gatekeep by
         | requiring the subscription for addins.
        
           | Centigonal wrote:
           | Microsoft spent a lot of effort to develop a really powerful
           | editing interface. If you can replace that interface with a
           | text input box, then their applications moat becomes a lot
           | shallower.
        
         | brian-jones wrote:
         | I run the Excel team at Microsoft. The experience you're
         | describing sounds like it's from the earlier versions of
         | Copilot in Excel that were genuinely limited.
         | 
         | Today, Excel Copilot takes a model-forward approach where we
         | give the models full access to Excel's capabilities. We give
         | customers the choice of the latest models from both OpenAI and
         | Anthropic, and we encourage the models to iteratively explore
         | the spreadsheet before taking action. It builds a full
         | understanding of the semantics and structure of the
         | spreadsheet, find issues in it, and ultimately gives you much
         | better results.
         | 
         | Copilot can write formulas, build PivotTables, create charts,
         | build multi-tab models, do multi-step analysis. The models are
         | quite proficient at it, and they do a great job. We have an
         | auto-mode which is the default where we pick the model for you,
         | but you can also select specific models if you have a
         | preference. I often see people switch between models to get the
         | benefit of diverse perspectives, similar to how a diverse team
         | approaches problems differently.
         | 
         | If you tried it a few months ago and walked away, it's worth
         | another look.
        
           | dgsegesg wrote:
           | Current model is inauthentically limited?
           | 
           | "If you tried it a few months ago and walked away, it's worth
           | another look." You shouldn't have shoved trash down people's
           | throats a few months ago then?
        
             | sqircles wrote:
             | > You shouldn't have shoved trash down people's throats a
             | few months ago then?
             | 
             | :s/You/MS
             | 
             | While I agree the widespread "race to market" with crap
             | probably does and should hurt the success of these "AI-
             | enabled apps," that particular area probably was not this
             | individuals decision.
        
               | shrdhdrhrdsh wrote:
               | It was this person's decision to mention their senior
               | role at MS then dump marketing drivel into our heads.
               | It's not his hand but he still eats with it.
        
           | drc500free wrote:
           | Does Copilot behave differently in Excel depending on whether
           | you got the premium subscription instead of what is included
           | with Business?
           | 
           | Many people I've talked to about Copilot don't realize that
           | the dedicated "Premium" Copilot is a completely different
           | experience than the "Basic/Lobotomized" Copilot that comes
           | with a standard Business subscription.
           | 
           | It's like you're running a freemium model where no one was
           | actually responsible for implementing the upsell, or making
           | sure the free version is useful and compelling. E.g. a
           | Copilot pane in Outlook that says it can't access your
           | emails, doesn't explain how, and doesn't mention an upgrade
           | path that will allow it to.
        
           | Abster1 wrote:
           | I've had a really good time with the new Copilot in Excel. I
           | like the model selector and tend to use Opus 4.6.
           | 
           | Q for you Brian, I have the Microsoft 365 Premium individual
           | plan ($200/yr). I got 50% off the premium plan as well when
           | Microsoft was offering discounts.
           | 
           | I've noticed when I use Claude or GPT through the Copilot
           | model selector I don't see any costs for my api usage
           | anywhere. Does Microsoft eat that for now?
        
             | brian-jones wrote:
             | Glad you're enjoying it! Opus 4.6 is great, and we've
             | started rolling out 4.7 today.
             | 
             | Your M365 Copilot Premium plan includes extensive usage of
             | the Copilot features, including the model selector, and
             | there are no additional API costs.
        
           | arbitrary_name wrote:
           | just tried it: i can't even use CSV files with Copilot...
           | 
           | Without coming across as overly rude, it is frankly
           | astonishing how limited Copilot is.
           | 
           | I do not like being an MS customer or user.
        
           | rdedev wrote:
           | Thanks for clarifying this. I was genuinely frustrated with
           | copilot due to the lack of features.
           | 
           | If it's possible please push your large business clients to
           | update office. I work for a multinational pharma company and
           | the copilot feature in excel deployed there is next to
           | useless
        
       | TrackerFF wrote:
       | 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.
        
         | jannyfer wrote:
         | Adding a tangential anecdote.
         | 
         | I asked GPT-5.4 High to draw up an architecture diagram in SVG
         | and left it running. It took over an hour to generate something
         | and had some spacing wrong, things overlapping, etc. I thought
         | it was stuck, but it actually came back with the output.
         | 
         | Then I asked it to make it with HTML and CSS instead, and it
         | made a better output in five seconds (no arrows/lines though).
         | 
         | SVG looks similar to the XML format of spreadsheets. I wonder
         | if LLMs struggle with that?
        
           | scronkfinkle wrote:
           | Claude's diagramming tool that they have built into their web
           | UI is my goto for this task. It's reliable enough that I
           | often will delegate to it first with what I need written in
           | prose instead of using mermaid/lucid diagram
        
           | cubefox wrote:
           | Gemini is very good with SVG, but I don't really see the
           | similarity to spreadsheets.
        
           | brett-jackson wrote:
           | I'd try asking it for a mermaid diagram. I think ChatGPT's
           | web interface will render them.
        
           | bob1029 wrote:
           | The LLMs seem to struggle at anything that isn't relatively
           | well anchored in whatever space. HTML documents have a lot of
           | foundation to them in the training data, so they seem to
           | perform well by comparison to other things.
           | 
           | I just spent a few hours trying to get GPT5.4 to write
           | strict, git compatible patches and concluded this is a huge
           | waste of time. It's a lot easier and more stable to do simple
           | find/replace or overwrite the whole file each time. Same
           | story in places like Unity or Blender. The ability to
           | coordinate things in 3d is really bad still. You can get
           | clean output using parametric scenes, but that's about it.
        
             | jqbd wrote:
             | Parametric scenes is the whole of Houdini and any node
             | based compositor etc. so there is some applications no?
        
         | angadsg wrote:
         | Engineer on ChatGPT for Excel here. Useful feedback. We have
         | improved the latency inside the add-in a lot and a lot more to
         | come. We also have the Fast, Standard and Heavy thinking modes,
         | where you can adjust the thinking time depending on the task
         | complexity. Curious to hear your feedback once you try this
         | out!
        
       | orliesaurus wrote:
       | Next do one for PowerPoint and Outlook
        
       | w2df wrote:
       | 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.
        
         | jimmydoe wrote:
         | saltman look so desperate.
         | 
         | meanwhile not that ant is genius, except the timing of dow
         | drama right before Iran war.
        
         | tokioyoyo wrote:
         | There's no real moat in feature set anymore. Within a given
         | timeframe, any company should be able to copy some features
         | from other companies. Thus the whole "distribution, marketing
         | and sales are the only things that matter nowadays" joke.
         | 
         | Obviously doesn't apply to everything, and there are some
         | features that are very hard to replicate. But still.
        
       | strongpigeon wrote:
       | 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 wrote:
         | 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 wrote:
           | 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.
        
             | Acmeon wrote:
             | 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.
        
               | strongpigeon wrote:
               | I don't think Excel web will ever be running the calc
               | engine browser side, no. The only way I could see this
               | happen would be via compiling the core to wasm, which I
               | don't think is worth the engineering effort.
               | 
               | Excel has this legacy (but extremely powerful) core with
               | very few people left that knows all of it. It has legacy
               | bugs preserved for compatibility reasons as whole
               | businesses are ran on spreadsheet that break if the bug
               | is fixed (I'm not exaggerating). The view code for
               | xldesktop is not layered particularly well either leading
               | to a lot of dependencies on Win32 in xlshared (at least
               | back then).
               | 
               | Is it doable? I'm sure. But the benefits are probably not
               | worth the cost.
        
               | Acmeon wrote:
               | Thanks for the interesting info! Yeah, maybe Excel web
               | will someday support local calculations via wasm, but for
               | now I think I will stick with Excel desktop with add-ins.
        
               | uticus wrote:
               | > Excel has this legacy (but extremely powerful) core
               | with very few people left that knows all of it.
               | 
               | Would love to hear more about this. Especially history
               | and comparison to Lotus etc.
        
               | strongpigeon wrote:
               | So the first thing that's important to understand is that
               | Excel is the product of another era. One where resources
               | like memory were very constrained and compilers and
               | optimizers weren't as good as they are today (so much so
               | that the Excel team at one point wrote their own because
               | MSVC sucked, but I digress)...
               | 
               | And so, a lot of the core code is used to that. Cell
               | formatting data for example is super tightly packed in
               | deeply nested unions to ensure that as little memory is
               | used to store that info. If something only needs 3 bits,
               | it'll only use 3 bits. The calc engine compiles all of
               | your formulas to its own (IIRC variable-instruction-
               | width) bytecode to make sure that huge spreadsheets can
               | still fit in memory and calc fast.
               | 
               | And a lot of it still carries the same coding and naming
               | practices that it started with in the 80s: Hungarian
               | notation, terse variable and file names, etc. Now, IMO,
               | Hungarian notation by itself is pretty harmless (and even
               | maybe useful in absence of an IDE), but it seemed to
               | encourage programmers to eschew any form of useful
               | information from variable names, requiring you to have
               | more context to understand "why" something is happening.
               | Like, cool, I have a pszxoper now (pointer to zero
               | terminated string of XOper), but why?
               | 
               | So the code is tight, has a lot of optimization baked in
               | and assumes you know a lot about what's happening
               | already.
               | 
               | But more importantly, a lot of "why" information also
               | just lives in people's head. Yes, some teams would have
               | documentation in an ungodly web of OneNote notebooks, or
               | spread across SharePoint pages, which had the least
               | useful search functionality I've ever witnessed, but
               | finding anything you wanted was hard. But that didn't use
               | to matter, since the core team had been there for a long
               | time, so you could ask them question.
               | 
               | That being said, I joined MSFT in 2012 and started
               | working on Excel closer to 2014. At that point,
               | heavyweight like DuaneC (who wrote like 10% of Excel and
               | I don't think I'm exaggerating) had already retired and
               | while others people were very knowledgeable in some
               | areas, nobody seemed to have a good cross view of the
               | whole thing.
               | 
               | You have to understand that I was in the Office
               | Extensibility team. We were building APIs for the _whole_
               | thing. I had to touch the calc system, the cells and
               | range, the formatting, tables, charts and images (the
               | whole shared oart system was interesting), etc. Answering
               | "How do I do X" was always a quest because you would
               | usually:
               | 
               | - Find 3 different ways of achieving it
               | 
               | - One of them was definitely the wrong way and could make
               | the app crash in some situations (or leak memory)
               | 
               | - All the people on the "blame" had left
               | 
               | - One of them was via the VBA layer which did some weird
               | stuff (good ol' pbobj)
               | 
               | - Be grateful that this wasn't Word because their
               | codebase was much worse
               | 
               | And so, a lot of the API implementation was trial and
               | error and hunting down someone who understood the data
               | structures. The fact that full sync and rebuild took
               | about 6 hours (you ran a command called `ohome` and then
               | you went home) meant that experimenting was sometimes
               | slow (at least incremental builds were OK fast). The only
               | lifeline back then was this tool called ReSearch2 that
               | allowed you to search the codebase efficiently.
               | 
               | But the thing is, once you got thing to work, they worked
               | really well. The core was solid and performant. Just
               | slightly inscrutable at time and not the kind of code
               | you're use to reading outside of Excel.
        
               | philipallstar wrote:
               | Surely picking that apart is a good idea. Even if it
               | costs a fortune, there have to be benefits.
        
             | DaiPlusPlus wrote:
             | > 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...
        
             | com2kid wrote:
             | 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.
        
               | p_ing wrote:
               | Never did this. WAC was the original version (integrated
               | with SharePoint Server). Everything was server-side.
        
               | strongpigeon wrote:
               | > WAC
               | 
               | Now that's an acronym that I had forgotten about.
        
               | com2kid wrote:
               | While working at MS I remember someone in the office team
               | saying that the original version of Excel online spun to
               | the actual Excel backend and had it output HTML instead
               | of the usual win32 UI. Was I misinformed by chance?
        
               | p_ing wrote:
               | Excel Online was a component of WAC. It was an ASP.NET
               | (and C++???) web application that used OAuth between
               | SharePoint Server and Exchange Server.
               | 
               | So I mean yes, you viewed Excel docs through a webpage
               | just like you do today via ODSP or OneDrive consumer. The
               | backend is completely different in the cloud service,
               | though.
        
               | strongpigeon wrote:
               | 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).
        
       | w2df wrote:
       | As someone that knows a high-flying portfolio manager who works
       | at a very well known firm that I wont name... I can confidently
       | state these tools are DOA. Ive spoken to them at length about the
       | nature of what these people actually do day-to-day. If you think
       | its just about using excel then you're already way off.
       | 
       | They (OAI+Anthropic) very much do not get exactly what these
       | people are doing in the job (accounting+corporate
       | finance+valuation+asset management) and what the actual
       | production process is. These tools are irrelevant, disrupt flow
       | and if anything just add noise to what one is doing.
        
         | z3c0 wrote:
         | This might be the first time I've seen a HN comment in a GPT
         | thread that actually reflects what the average business user
         | sees in GPT products.
         | 
         | They don't do the job, reliably or well. No amount of wishful
         | thinking or extra tokens will change that.
        
           | w2df wrote:
           | No surprise really.
           | 
           | Remember when Steve said 'The computers for the rest of us'?
           | 
           | I suppose it isn't a surprise. Are researchers/generally
           | geeky people meant to be able to relate to the average
           | person's day-to-day beyond their sphere? Lmao.
           | 
           | You can't produce stuff for people you don't understand.
           | Understand being a very key term.
        
         | brcmthrowaway wrote:
         | I know the firm - it's RenTech.
        
           | w2df wrote:
           | nah the firm in question has much higher AUM.
        
             | brcmthrowaway wrote:
             | Citadel
        
         | esafak wrote:
         | Why are they irrelevant? You do not say anything.
        
           | w2df wrote:
           | I care not to. I hope Anthropic and OAI keep burning money on
           | stuff that's DOA.
           | 
           | I know there are employees of those firms here that would
           | love to know. But nah lmao.
        
           | airstrike wrote:
           | Because the challenge is in the space between apps, not in
           | the apps themselves.
        
         | airstrike wrote:
         | As a former investment banker, I mostly agree. This is probably
         | 10% of the work
        
           | w2df wrote:
           | Even 10% might be generous.
           | 
           | I bet the bozos at OAI and Anthropic think a person who deals
           | with stuff like cost of capital is going to go ask an LLM for
           | it.. when in reality the individual needs to know how/why
           | they chose what they did.
           | 
           | Comical stuff.
        
       | HerbManic wrote:
       | 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.
        
         | kgeist wrote:
         | I wonder why it's so bad. Do they just paste a CSV into the raw
         | model? Because in my experience, even small local models can
         | handle it reasonably well if the harness forces them to write &
         | run a Python script that parses the table and performs the
         | calculations, instead of relying solely on next-token
         | prediction.
        
       | p_ing wrote:
       | 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.
        
         | strongpigeon wrote:
         | > I'm sure there's some edge cases, but MSFT has been moving
         | away from OAI.
         | 
         | You're not wrong, but you'd think that given their 27% stake in
         | OpenAI they'd put more weight behind ChatGPT integration.
        
           | p_ing wrote:
           | Based on my discussion with DSEs, enterprises have not been
           | impressed in the results of "Copilot", i.e. OAI models. MSFT
           | has been replacing (or changing the default) to Claude across
           | a variety of Copilot endpoints.
        
           | ralph84 wrote:
           | MSFT also has a stake in Anthropic (although much less than
           | 27%) and they host Anthropic models in Foundry now. The end
           | game for MSFT has always been being the compute provider, so
           | MSFT is just as happy to use any model as long as it's
           | running in Foundry.
        
       | Acmeon wrote:
       | 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.
        
         | p_ing wrote:
         | That's the nature of these add-ins. Modern Add-ins are all
         | little XML frames with some JS or whatever. All processing
         | occurs server-side, hosted by the add-in publisher.
         | 
         | This is counter to the old (security nightmare) COM model where
         | processing could be local.
        
           | strongpigeon wrote:
           | To clarify: add-ins are essentially web pages. They can do
           | some processing client side if they want, but yeah in the
           | case of a ChatGPT add-in it's not like they're running the
           | model in a web frame.
        
             | sotix wrote:
             | Exactly. My company's add-in is a React app, which can be
             | fun to debug with the limited developer tools in
             | Word/Excel's browser.
        
         | angadsg wrote:
         | Hi, engineer on this add-in. Fair concern but we never train on
         | any of our business or enterprise user data, or if you have
         | opted-out of training on your ChatGPT account.
        
           | Avicebron wrote:
           | Forgive my ignorance. How do you folks manage context
           | retention? Say if someone had a sensitive excel document they
           | wanted inference done over, how is that data actually sent to
           | the model and then stored or deleted?
           | 
           | It seems one of the biggest barriers to people's adoption is
           | concern over data leaving their ecosystem and then not being
           | protected or being retained in some way.
           | 
           | Is this is an SLA that a small or medium sized company could
           | get?
        
             | p_ing wrote:
             | If you're concerned, you don't send it outside of the M365
             | boundary and presumably your admin has Purview Sensitivity
             | Labels in place covering the document to prevent such
             | activity.
        
               | Avicebron wrote:
               | Doesn't that mean you can't actually use it for those
               | sensitive documents?
        
               | p_ing wrote:
               | Correct.
        
               | Avicebron wrote:
               | {EDIT} English and or the concept of written word may be
               | foreign to you. Thank you for your assistance.
        
               | p_ing wrote:
               | Not sure why you'd state that. 'Correct' is a
               | grammatically correct and complete sentence to your
               | question.
        
           | Acmeon wrote:
           | Yeah, I was expecting that you do not train on business or
           | enterprise user data. However, I am not just worried about
           | "training", but also about "sharing". Furthermore, I am
           | worried about cases where an individual has chosen to
           | integrate an add-in and then inadvertently leaks sensitive
           | data.
           | 
           | However, it may be important to note that these security
           | considerations are relevant for most Office Add-Ins (and not
           | just the ChatGPT add-in).
        
       | _pdp_ wrote:
       | Why though? What is the point of this? I thought they are
       | building towards an AGI.
        
       | keyle wrote:
       | Copilot is so bad that chatGPT is offered to replace it.
       | [for] ... users outside the EU.
       | 
       | hmm
        
         | p_ing wrote:
         | Your comment is recognized as low effort, but Copilot has been
         | OAI models behind the scenes. For enterprise customers, quickly
         | being replaced by Sonnet as a default.
        
           | keyle wrote:
           | Thank you for high effort response!
           | 
           | I would never use Copilot for anything useful, but I do use
           | OpenAI products.
           | 
           | It doesn't matter when you use something else wholesale under
           | the covers, if you botch the token spent...
        
             | p_ing wrote:
             | Token expenditure isn't a concern for Copilot users. They
             | don't see that form of cost model, just a flat monthly (or
             | yearly) price for a user license.
        
               | keyle wrote:
               | Exactly, and how do you think it's rigged in the setup?
               | You're not getting top tier OpenAI service with Copilot
               | was my point.
        
               | p_ing wrote:
               | Microsoft runs the model, not OAI.
        
       | 1970-01-01 wrote:
       | This is a drop-in database analysis tool and nobody knows it.
       | Most Excel users are using Excel as a half-baked database instead
       | of as a spreadsheet.
        
       | _doctor_love wrote:
       | I have been waiting for this moment. Whatever AI vendor
       | establishes a strong beachhead in being competent at Excel is
       | going to do _extremely_ well.
       | 
       | Microsoft, being Microsoft, will find a way to win no matter who
       | that vendor ends up being.
        
       | mritchie712 wrote:
       | 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
        
       | airstrike wrote:
       | This is quite cool, but it's only the tip of the iceberg.
       | 
       | Building an agent that can securely access systems of records,
       | external data sources, and other files in your workspace--with
       | context for the work you do _outside_ of Excel--is where the
       | revolution is at.
        
       | angadsg wrote:
       | 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!
        
         | rahimnathwani wrote:
         | How well does this work compared with using GPT-5.4 in
         | Nicopreme's Pi for Excel?
        
           | howdareme9 wrote:
           | have you got a link to this?
        
             | rahimnathwani wrote:
             | Sorry, I got the author wrong.
             | 
             | It's here: https://github.com/tmustier/pi-for-excel
        
         | e38383 wrote:
         | I probably could find some really useful things for it to help
         | me ... but all software nowadays only works outside my earth
         | region :(
         | 
         | This time even for pro.
        
         | carderne wrote:
         | What API/approach does it use to edit sheets?
         | 
         | I made a CLI (+skill) so agents could edit files with verbs
         | like `insert A1:A3 '[1,2,3]'`, but did some evals and found it
         | underperformed Anthropic's approach (just write Python).
        
         | bsenftner wrote:
         | I've had a spreadsheet integrated with ChatGPT API for a few
         | years already. It really was not until GPT-5.4 that the models
         | were able to actually be useful.
         | 
         | What is the data model that you use for the spreadsheet itself?
         | I found I could create a chat completion persona that believed
         | it is one of the developers of a popular open source
         | spreadsheet, and I put this "agent" directly inside the open
         | source spreadsheet. I did this before tool calling was
         | available at all, so I made my own system for that, and the
         | "tools" are the API of that open source spreadsheet. My
         | agent(s) that operate like this can do anything the spreadsheet
         | can do, including operate the spreadsheet engine from the
         | inside.
        
         | hazelnut wrote:
         | Do you also have Google Spreadsheets on your radar?
        
       | bewal416 wrote:
       | Thanks, but wake me up when there's an actually good AI embedded
       | directly in Google Sheets
        
       | mynameisneely wrote:
       | The interesting question isn't whether ChatGPT can do Excel. It's
       | whether general-purpose AI beats role-specific AI for serious
       | work. I'm building in marketing and the pattern I keep running
       | into is that the blank canvas of ChatGPT is actually the problem
       | for most people, not the solution. Analysts, marketers, ops folks
       | don't want a chat interface. They want something that already
       | knows the shape of their job. Horizontal tools win demos.
       | Vertical tools win retention. My bet is the Excel crowd ends up
       | somewhere closer to Rows or Equals than to a chat sidebar, but I
       | could be wrong.
        
       | TacticalCoder wrote:
       | 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.
        
       | arjie wrote:
       | 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.
        
         | killerdhmo wrote:
         | I mean, you're wrong. As a Xoogler, everything was in Sheets.
         | Our roadmap was in Sheets. It's more they don't care.
        
         | AznHisoka wrote:
         | I love Sheets, but I dont care for using Gemini to interact
         | with Sheets. It seems like a recipe for disaster. Do I really
         | want it to muck around with thousands of rows and no intuitive
         | way to diff its changes? Nope, sticking with basic Sheets
        
         | buccal wrote:
         | You should try MS Copilot which uses open source Python
         | libraries to interact with Office file formats.
         | 
         | The libraries themselves are OK, but MS uses them stupidly. If
         | you want to fill out some form in DOCX or XSLX format you will
         | get broken formatting. And this is from Office company.
        
           | devmor wrote:
           | I recently experimented with trying to generate a passable
           | slide deck from a script and outline I had written
           | beforehand. The ChatGPT integration built into Powerpoint was
           | abysmally bad. Like to the point it was embarrassing as a
           | product.
           | 
           | Claude one-shot something with a Python script that was
           | pretty okay.
        
           | darkwater wrote:
           | Obviously. Because they didn't train the model on proprietary
           | MS code. Which is bad but also good in some way, as it might
           | force MS to support better their formats in the open source
           | world.
        
         | charlieflowers wrote:
         | I'm having great luck having Claude Code generate, read, and
         | update spreadsheets by writing Python code that uses gspread.
        
           | VadimPR wrote:
           | Can it work with comments in sheets as well? When I looked
           | into it, that seemed like a limitation.
        
           | speleding wrote:
           | It also works fine with Ruby and the "caxlsx" gem. Codex
           | works fine with it as also.
        
           | arjie wrote:
           | Surprisingly even small models can do this quite well. I have
           | Sonnet on a claw-like generate something based on my emails,
           | airbnb receipts, and so on, and it was perfect and it could
           | edit fields and whatnot, but the Gemini tool can't do
           | anything.
        
         | yabutlivnWoods wrote:
         | My local models interact with Sheets exclusively over the API
         | with Python scripts I been curating for years
         | 
         | Given how well the API works, that we are discussing Googlers,
         | my guess is that's how they dog food their services.
         | Programmers don't get hired by Google for mouse skills.
         | 
         | The GUI is for spot checking results, final presentation.
         | 
         | If you're sitting there point-n-clicking everything into place
         | perhaps consider you are doing it wrong.
        
           | beepdyboop wrote:
           | That sounds like an extremely narrow use case, compared to
           | what the vast majority of Sheets users will be comfortable
           | with
        
             | mbreese wrote:
             | At the same time, it makes some sense... the programmers
             | for a system aren't always the best users of a system. So
             | if you're expecting them to dogfood their own system
             | (Google Sheets), you might find that they test/interact
             | with the system primarily through the API and not the GUI.
             | 
             | I have no idea if they do or not, but it's a plausible
             | explanation...
        
             | yabutlivnWoods wrote:
             | Use case feels like the wrong term.
             | 
             | Do you mean restricted workflow? Googles APIs are pretty
             | much 1:1 to the GUI
             | 
             | And using Python makes it trivial to copy-paste out of
             | files and other APIs with one run of Python
             | 
             | Versus all the fiddling in browser tabs with a mouse, it
             | actually affords an incredibly wide set of options to
             | quickly collate and format data
        
           | intended wrote:
           | How? This argument would make sense if sheets _wasn't_
           | targeted at a general audience.
        
         | dminik wrote:
         | Yeah, the Sheets integration is weird. It's usually ok when it
         | wants to place something down the first time. But then it seems
         | incapable of making any changes to it. Or even acknowledging
         | the data in the sheet. What's up with that?
        
         | bdcravens wrote:
         | I tried it the other day to work on some exported CSVs when
         | doing my taxes. I was finally able to get it to do what I
         | wanted, but it was definitely an exercise, feeling like I was
         | talking to Chat GPT from a couple of years ago. (as in a really
         | smart but easily distracted and confused child)
        
         | nunez wrote:
         | Agreed; I was also shocked by how limited it was. Same with the
         | Slides integration.
        
       | whalesalad wrote:
       | Does a highly performant XLSX tool exist? I want to be able to
       | open a 500k row, 60+ column table in Excel and manipulate it at
       | 60+ FPS. Zero lag. I feel like Excel has never - ahem - excelled
       | in this department. Libreoffice comes close and I enjoy it on
       | Linux, but on my M2 Macbook Air it struggles.
        
         | rpearl wrote:
         | Try https://rowzero.com ? We have written a much faster
         | spreadsheet engine and regularly work with 10M+ row datasets
        
       | DeathArrow wrote:
       | It seems to not be available in EU, possibly due to regulations.
        
       | Bishonen88 wrote:
       | FAQ: Is it available worldwide? A: Yes. (...) outside the EU.
       | 
       | So, yes but no. Not that I care, but the answer to the above
       | question is a no, and should start with No.
        
       | tills13 wrote:
       | These AI in Excel products are a financial crisis waiting to
       | happen. Or maybe just Enron but stupider.
        
       | flexie wrote:
       | Do anyone here know if OpenAI plans on introducing a Word add-in,
       | like Claude for Word?
        
       | Instagraf wrote:
       | Nice addition for get my head around those narley formulas ...
       | and without having to jump out of the Sheet.
        
       | thih9 wrote:
       | > 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?
        
       | linzhangrun wrote:
       | This should have been implemented when Microsoft launched Copilot
       | two years ago. Instead, they'd rather hijack the right Ctrl on
       | every computer than do this.
        
       | mentalgear wrote:
       | More like ChatGPT for Claude for Excel .
        
       | kbos87 wrote:
       | From time to time I've tried using ChatGPT for financial
       | modeling, and I have to say my experiences don't inspire much
       | confidence.
       | 
       | Just this past week I used it to generate a simple model of a few
       | different scenarios related to an investment property I own.
       | 
       | The first problem I ran into is that it was unable to output a
       | downloadable XLS file. Not a huge deal - it suggested generating
       | CSV tables I could copy/paste into a spreadsheet. The outputs it
       | gave me included commas in a handful of numbers over 1,000 (but
       | not all of them!) which of course shifted cells around when
       | brought into Google Sheets. We pivoted our approach to TSV and
       | solved this problem. Big deal? No. Seemingly basic oversight?
       | Absolutely.
       | 
       | This is where the real fun began. Once I started to scrutinize
       | and understand the model it built, I found incorrect references
       | buried all over the place, some of which would have been
       | extremely hard to spot. Here's my actual exchange with ChatGPT:
       | 
       | - - - - - - - - - -
       | 
       | > Can you check the reference in cell F3? It looks like it's
       | calling back to the wrong cell on the inputs tab. Are there
       | similarly incorrect references elsewhere?
       | 
       | > Yes, F3 is incorrect, and there are multiple other incorrect
       | references elsewhere: (It listed about 30 bulleted incorrect
       | references)
       | 
       | Bottom line - - Many formulas point to the wrong Inputs row
       | because of the blank lines - The Sell + Condo section also has a
       | structural design problem, not just bad references.
       | 
       | The cleanest fix is for me to regenerate the entire AnnualModel
       | TSV with: - all references corrected - all 15 years included -
       | the condo scenario modeled properly with a separate housing asset
       | column
       | 
       | - - - - - - - - - -
       | 
       | This was me asking about the exact output I had just received
       | (not something I had made any changes to or reworked.)
       | 
       | There are plenty of domains where I have enough faith and error
       | tolerance to use ChatGPT all day, but this just sends a chill
       | down my spine. How many users are really going to proof every
       | single formula? And if I need to scrutinize to that level of
       | detail, what's the point in the first place?
        
       | chux52 wrote:
       | How do the OpenAI models/reasoning effort map to Fast, Standard,
       | Heavy in the add-in?
        
       | dangoodmanUT wrote:
       | On this episode of "chatgpt just killed my startup"
       | 
       | Tune in for the next episode: Word
        
         | Aboutplants wrote:
         | Word was the first thing killed
        
       | dirasieb wrote:
       | doesn't seem to be available for excel on macOS, disappointing
        
       | dueltmp_yufsy wrote:
       | I already use AI to help recall the various macros. I think this
       | is a great use case for real world impact of AI. So many jobs
       | still rely on Excel as central facet of analysis. I'm looking
       | forward to trying it myself.
        
       | ozgurds wrote:
       | We were already using AI in excel but manuallay copy pasting the
       | macros and doing the things by ourselves. This will make us save
       | really much time. When you have automated macros it is really fun
       | to deal with excels.
        
       | tboughen wrote:
       | 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.
        
       ___________________________________________________________________
       (page generated 2026-04-16 23:02 UTC)