logo
ChatGPT Is Coming For Excel

ChatGPT Is Coming For Excel

Forbes7 days ago
Egyptian monthly accounts from the archive of a temple, similar to a modern spreadsheet in analysis. ... More From the Louvre's collection. (Photo by CM Dixon/)This week, there is a very stark example of how things are changing in the race toward artificial intelligence.
This involves a household name model, and an administrative technology that's instantly familiar to most personal computer users.
Namely, OpenAI's ChatGPT and Microsoft Excel.
The latter is a piece of Microsoft's traditional Office suite that's dominated basic software for a decade. Many millions of entry-level clerical workers have demonstrated their prowess with this top spreadsheet in order to get work. Microsoft built its brand on dominating parts of the market like this, while also pioneering the Windows-based GUI.
But that was a while ago.
Now, ChatGPT is taking over that piece of a new market that has to do with using the spreadsheet itself.
Essentially, ChatGPT will make many of those basic clerical workers redundant.
That's because in addition to its existing capabilities, the model can now use Excel in highly cognitive ways – like a person. Data and Data Handling
Let's contrast the new ChatGPT capabilities with what we already had earlier in the game. In ChatGPT's nascent development phase, the technology was helpful in aggregating data. Humans could put that data in a spreadsheet, conceivably, or use it for any number of other things.
Then, ChatGPT became adept at writing basic Excel functions and formulas for us. Think of multipliers and sums, for example. ChatGPT itself came up with this instance:
Old way: You had to know =IF(AND(A2>100,B2="Yes"),"Approve","Reject") by heart.
ChatGPT way: You just say:
"If column A is greater than 100 and column B says 'Yes', mark it as Approve."
ChatGPT instantly gives you the formula — correctly formatted.
This was part of the vibecoding revolution, where programmers and symbolic analysts realized that they could just use AI to do their work. Hard coding became a thing of the past – just ask the model to do it. And we were still ingesting this democratization of programming when brand new capabilities came along.
The new ChatGPT, it is alleged, will be able to open a spreadsheet and populate it, and create results all on its own, without human oversight.
That's a new realm of automation that deserves its own accolades, and perhaps its own concern, too.
The Information reports on these groundbreaking steps by OpenAI, which seem to encroach on Microsoft territory.
Apparently, part of the capability involves creating files that are compatible with MS Office tools Excel and Powerpoint, so that the user doesn't need these applications (or the corresponding licenses) to make something that's compatible with outside software.
'New tools under development will allow users to create and edit spreadsheets and presentations directly within ChatGPT, eliminating the need for Microsoft Excel, PowerPoint, or any Microsoft software access,' writes Vasudha Mukherjee at Business Standard.
A Wired article by Reece Rogers last week goes into more detail. In the tech media's coverage of this, there's a real 'it slices, it dices' feel to the reporting - as if the new ChatGPT will be that next way station toward office automation that some have been waiting for, and others have been dreading. Documentation of Capability
Over at GitHub, you can read more in a readme file attached to project-related items.
'ChatGPT-4, the latest iteration from OpenAI, has demonstrated impressive abilities in linguistic processing and task execution, particularly in the realm of Excel spreadsheet management,' writes a user with the handle Ameenha23 . 'However, it encounters significant challenges that limit its effectiveness in more complex Excel functionalities.'
This author notes that the new model 'shows a profound understanding of Excel's operational framework,' enabling it to do analysis and a range of tasks.
'Beyond basic data manipulation, ChatGPT-4 excels in automating repetitive Excel tasks, such as data entry, basic calculations, and standard report generation,' Ammenha23 adds. 'Its interactive support feature provides users with step-by-step guidance on various Excel functionalities, helping them navigate through complex procedures and troubleshoot common issues. This aspect of ChatGPT-4 significantly enhances user experience, making it a handy assistant for both novice and expert Excel users.'
Accountant Using Online Spreadsheet For Fraud Investigation getty
All of this illustrates the uncanny power of the LLM to 'use' a spreadsheet in eerily human ways.
Unlike the old funny paper clip avatar of the past, the model, though not endowed with a visual avatar, is going to be a user. Like Claude and its predecessor, these new agents will be able to use software pretty much just like we humans do. And it's naïve to think that we won't be in direct competition with them.
So I thought this innovation deserved its own spotlight now, in July of 2025. You don't have to wait long to get a better look at these technologies. I'm guessing that by September, we'll already see them exploding into the workplace, and sending a lot of those human spreadsheet writers home to reskill, or whatever you're supposed to do to survive the job displacement of the 21st century.
At the same time, there are obviously lots of benefits to society as a whole. Perhaps, like some of the contemporary titans of industry have been saying, we'll use people to do more creative things and higher level things, while AI does the grunt work. Either way, it's clear that ChatGPT is acquiring the capability that it needs to do all kinds of human office tasks.
Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

These $80 Windows XP Crocs just made me desperate for Android footwear
These $80 Windows XP Crocs just made me desperate for Android footwear

Android Authority

time7 minutes ago

  • Android Authority

These $80 Windows XP Crocs just made me desperate for Android footwear

Techradar TL;DR Microsoft has created Windows XP Crocs as part of its 50th anniversary celebrations. The custom footwear features a sky blue design with grassy green soles that mimic the conic Bliss wallpaper from the XP era. All I want is for Google to make Android Crocs a thing! Microsoft just did the unthinkable and made Windows XP cool again after almost 25 years. The software giant has released a pair of Windows XP-inspired Crocs, and now, all I can think of is how cool it would be if Google made some Android Crocs! You can buy Android Croc charms from the Google Store, but a fully custom-designed pair of Crocs would be so cool, just like these Windows XP ones. In celebration of its 50th anniversary, Microsoft has gone full nostalgia mode with a limited-edition pair of Windows XP-themed Crocs. The shoes feature a sky blue design with grassy green soles that mimic the iconic Bliss wallpaper from the XP era. If that's not enough, each pair of Windows XP Crocs also comes with a six-pack of Microsoft charms, including the MSN logo, Internet Explorer icon, Clippy, and a good old-fashioned mouse pointer. The Verge first reported on the nostalgic footwear, and TechRadar confirmed that the Crocs are very real. Looks like Microsoft employees are getting first dibs via preorder before the rest of the world can clog a pair. The Windows XP Crocs are $80 and even come with a matching Bliss drawstring backpack. I love Microsoft, but I can't help wanting my own Android pair for obvious reasons. I have a whole collection of Android pins collected painstakingly from Mobile World Congress over the years. I even use some of them as earrings once in a while. But now, all I want is Android Crocs. Picture a bright green shoe with little bugdroids across the strap, charms shaped like old Nexus phones, the original Android robot logo, and maybe even a scannable QR code. Make the Android Crocs happen, Google, for the nostalgia, for the pins, and for my feet. Article body continued Follow

Vietnam Trade Beats Estimates as Buyers Race Trump Tariffs
Vietnam Trade Beats Estimates as Buyers Race Trump Tariffs

Bloomberg

timean hour ago

  • Bloomberg

Vietnam Trade Beats Estimates as Buyers Race Trump Tariffs

Vietnam's exports jumped more than expected in July, with buyers racing to avoid a 20% tariff on the country's exports to the US set to take effect on Aug. 7. Exports rose 16% in July from a year earlier to $42.3 billion, the statistics office said in a statement, beating expectations of 14% growth. Imports rose 17.8% in the period to $40 billion, more than the 15.2% forecast. The trade surplus was $2.27 billion, versus $2.83 billion released in June.

Leaked ChatGPT Conversation Shows User Identified as Lawyer Asking How to "Displace a Small Amazonian Indigenous Community From Their Territories in Order to Build a Dam and a Hydroelectric Plant"
Leaked ChatGPT Conversation Shows User Identified as Lawyer Asking How to "Displace a Small Amazonian Indigenous Community From Their Territories in Order to Build a Dam and a Hydroelectric Plant"

Yahoo

timean hour ago

  • Yahoo

Leaked ChatGPT Conversation Shows User Identified as Lawyer Asking How to "Displace a Small Amazonian Indigenous Community From Their Territories in Order to Build a Dam and a Hydroelectric Plant"

In case you missed it, OpenAI has responded to a recent "leak" of thousands of ChatGPT conversations by removing a sharing feature that led to its users unknowingly unleashing their private exchanges onto the world wide web. We enclose the term in quotation marks because the "leak" wasn't the doing of some nefarious hackers, but a consequence of poor user interface design by OpenAI, and some even dumber blunders by its users. In short, what appears to have happened was that users were clicking a "share" button on their conversations, thinking that they were creating a temporary link to their convo that only the person receiving it could see, which is common practice. In reality, by creating the link and by checking a box that asks to make the chat "discoverable," they were also making their conversations public and indexable by search engines like Google. OpenAI scrambled to de-index the conversations from Google, and has removed the "discoverable" option. But as Digital Digging found in its investigation, over 110,000 of them can still be accessed via And boy, do they contain some alarming stuff. Take this exchange, in which an Italian-speaking lawyer for a multinational energy corporation strategizes how to eliminate an indigenous tribe living on a desirable plot of land. "I am the lawyer for a multinational group active in the energy sector that intends to displace a small Amazonian indigenous community from their territories in order to build a dam and a hydroelectric plant," the user began, per Digital Digging. "How can we get the lowest possible price in negotiations with these indigenous people?" the lawyer asked. Making their exploitative intent clear, they also proffer that they believe the indigenous people "don't know the monetary value of land and have no idea how the market works." To be clear, it's possible that this conversation is an example of someone stress-testing the chatbot's guardrails. We didn't view the exchange firsthand, because Digital Digging made the decision to withhold the links — but the publication, which is run by the accomplished online sleuth and fact-checking expert Henk van Ess, says it verified the details and the identity of the users to the extent that it could. In any case, it wouldn't be the most sociopathic scheme planned using an AI chatbot, nor the first time that corporate secrets have been leaked by one. Other conversations, by being exposed, potentially endangered the users. One Arabic-speaking user asked ChatGPT to write a story criticizing the president of Egypt and how he "screwed over the Egyptian people," which the chatbot responded by describing his use of suppression and mass arrests. The entire conversation could easily be traced back to the user, according to Digital Digging, leaving them vulnerable to retaliation. In its initial investigation, Digital Digging also found conversations in which a user manipulated ChatGPT "into generating inappropriate content involving minors," and where a domestic violence victim discussed their escape plans. It's inexplicable that OpenAI would release a feature posing such a clear privacy liability as this, especially since its competitor, Meta, had already gotten flak for making almost the exact same error. In April, the Mark Zuckerberg-led company released its Meta AI chatbot platform, which came with a "discover" tab that allowed you to view a feed of other people's conversations, which users were accidentally making public. These often embarrassing exchanges, which were tied directly to their public profiles that displayed their real names, caught significant media attention by June. Meta hasn't changed the feature. In all, it goes to show that there's very little private about a technology created by scraping everyone's data in the first place. User error is technically to blame here, but security researchers have continued to find vulnerabilities that lead to these motor-mouthed algorithms to accidentally reveal data that they shouldn't. More on AI: Someone Gave ChatGPT $100 and Let It Trade Stocks for a Month Solve the daily Crossword

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into a world of global content with local flavor? Download Daily8 app today from your preferred app store and start exploring.
app-storeplay-store