Microsoft says its Agent Mode in Excel has an accuracy rate of 57.2 percent in SpreadsheetBench, a benchmark for evaluating an AI model’s ability to edit real world spreadsheets.
It generates 42.8% bullshit.
Microsoft says its Agent Mode in Excel has an accuracy rate of 57.2 percent in SpreadsheetBench, a benchmark for evaluating an AI model’s ability to edit real world spreadsheets.
It generates 42.8% bullshit.
So let me fast forward a bit, ->underpaid stressed out techworkers in the global south pretending to be AI for incompetent upper management in wealthy countries?
Not related but does global south refer to south of the equator or just everything south of north America?
I don't know if it is a perfect term, but it doesn't literally refer to any specific "South", rather I think it is a reference to the coincidence that many of the heavily industrialized empires of the 18th, 19th and 20th centuries have been in the northern hemisphere, and the general colonial power dynamic therein set up has lead to the term "Global South" meaning pretty much anywhere that has gotten the short end of the colonialism stick, vs the long end.
https://en.m.wikipedia.org/wiki/Global_North_and_Global_South
LLMs can't count. Can't add. Can't deal with actually large datasets
How is excel a good fit for vibe-coding?
LLMs lose context over a short session. They all have input limits. Very small input limits usually. Best it can probably do is suggest formulas for you based on your natural language, maybe some copy/paste. Which means it can beat a 9 year old, great news everyone! Or show a help article on pivot tables (which the help function already does!)
Excel is very simple to work with, hence its ubiquity. LLMs also get shit wrong about half the time, way more than half with difficult things ime. Meaning they cost experienced operators time, a few studies are showing this now with coding. And are expensive as fuck. And slow as fuck. And reduce capacity for learning. Meaning they actually cap what excel can achieve, as the user won't grow at the same rate, renoving the one advantage excel actually has: the learning rate is phenomenal
The C-Suite which insisted on this integration is basically an subservient idiot themselves at this stage who doesn't understand their product, their market fit, or their userbase. They should replace thenselves with an LLM
The problem with being a pragmatic LLM user is that you have on one side corporate America shoe-horning the tech in mediocre products none wants, and on the other side a large portion of the internet who loathe it but don't use it and don't even know what it does. Those conversations never go anywhere man. You're talking to someone who thinks accuracy of 57% on SpreadsheetBench means the model gives wrong answers 42% of the time.
Hate to agree with Microsoft but yeah, Excel is probably a great place to introduce an LLM. It's in that sweet spot between natural language and light programming, in an environment with math baked in so you don't really care about the model's accuracy or exact recall. All the data is here, and the model only has to manipulates cell numbers and writes formulas in this dumbed down language.
I'm sure you can get away with pretty small models too. It doesn't need super human knowledge to implement 90% of common Excel use cases, and i suspect in real world scenarios the accuracy must be pretty interesting.
It could be good to layer in standard machine learning (ML), and it already does have some features (like line of best fit).
However, in today's context AI means LLMs, and that is not a good fit due to its unpredictability.
Microsoft Clippy says "Hello. You appear to be making an invoice. I can help!" Only we're not making an invoice, and Clippy cannot help.
I can count the number of times that I have looked in an Excel sheet and thought, "I wish this was subtly wrong due to subtle changes made by a hallucination engine." It is zero.
Unfortunately the world has become so divorced from reality it no longer matters whether something is true. It only matters whether you can convince someone it looks or feels true. Management wants subtle changes made by a hallucination engine because it doesn't matter if they fail, they still get their golden parachute and move on to another company they get to ruin 🤷♀️
I can count the number of times that I have looked in an Excel sheet and thought, "I wish this was subtly wrong due to subtle changes made by a hallucination engine." It is zero.
lol. This is beautiful.
In the same way vibe coding has transformed software development
So, that is to say, they expect it to have no impact on serious work whatsoever?
Future generations are already looking at us with great deep unforgiving disappointment. We failed as a species.
all 33 comments