Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I’m worried that they put co-pilot in Excel

simonwillison.net

Post reply on HN
Print view View original

221–230 of 346 posts

Re: I’m worried that they put co-pilot in Excel

#221

Post by 7thaccount »

simonw wrote: post #146
7thaccount wrote: post #135

Earlier quoted context omitted.

I think that is a fair point too. The person that builds the Tableau dashboard could just send Brenda a screenshot once a month and that saves everyone time.

A screenshot of a Tableau dashboard is possibly the most dangerous form of internal data communication there is, because it entirely removes any chance of digging into that dashboard and figuring out what queries created it and spotting the incorrect assumptions they made along the way. A hill I will die on is that business analytics need "view source" or they aren't worth the pixels they are rendered with.

I respectfully disagree. The amount of folks in upper management that can actually use something like Tableau is very small. However it doesn't matter as none of those people have the time outside of very small businesses which probably don't need it anyway. The business intelligence person is supposed to deliver succinct insights to upper management to act on, not say "here's a cool system I built you... figure it out yourself". Executives aren't getting paid $$$$$$$$ to do data analysis. Hopefully I'm not misrepresenting your point.

Re: I’m worried that they put co-pilot in Excel

#222

Post by faeyanpiraat »

stavros wrote: post #185
wat10000 wrote: post #169

Earlier quoted context omitted.

Programs can be very close to 100% reliable when made well. In my life, I've never seen `sort` produce output that wasn't properly sorted. I've never seen a calculator come up with the wrong answer when adding two numbers. I have seen filesystems fail to produce the exact same data that was previously written, but this is something that happens once in a blue moon, and the process is done probably millions of times a…

> Programs can be very close to 100% reliable when made well. This is a tautology. > I've never seen a calculator come up with the wrong answer when adding two numbers. https://imgz.org/i6XLg7Fz.png > And technically, most bugs are predictable in theory, they just aren't known ahead of time. When we're talking about reliability, it doesn't matter whether a thing can be reliable in theory, it matters whether it's reli…

You mixed up correctness and reliability.

The ios calculator will make the same incorrect calculation, but reliably, every time.

Re: I’m worried that they put co-pilot in Excel

#223

Post by simonw »

7thaccount wrote: post #221
simonw wrote: post #146

Earlier quoted context omitted.

A screenshot of a Tableau dashboard is possibly the most dangerous form of internal data communication there is, because it entirely removes any chance of digging into that dashboard and figuring out what queries created it and spotting the incorrect assumptions they made along the way. A hill I will die on is that business analytics need "view source" or they aren't worth the pixels they are rendered with.

I respectfully disagree. The amount of folks in upper management that can actually use something like Tableau is very small. However it doesn't matter as none of those people have the time outside of very small businesses which probably don't need it anyway. The business intelligence person is supposed to deliver succinct insights to upper management to act on, not say "here's a cool system I built you... figure it o…

The view source link isn't there so upper management who don't know SQL can look at it. It's there so other people in the organization who do know SQL have the opportunity to check the work.

At my last large employer I genuinely lost count of the number of times I saw a BI report which pulled numbers from our data warehouse... and then found out it had misinterpreted a key detail because the engineering team had changed some table design six months ago and the data analysis team hadn't been told about the change.

Re: I’m worried that they put co-pilot in Excel

#225

Post by stavros »

faeyanpiraat wrote: post #222
stavros wrote: post #185

Earlier quoted context omitted.

> Programs can be very close to 100% reliable when made well. This is a tautology. > I've never seen a calculator come up with the wrong answer when adding two numbers. https://imgz.org/i6XLg7Fz.png > And technically, most bugs are predictable in theory, they just aren't known ahead of time. When we're talking about reliability, it doesn't matter whether a thing can be reliable in theory, it matters whether it's reli…

You mixed up correctness and reliability. The ios calculator will make the same incorrect calculation, but reliably, every time.

Don't move the goalposts. The claim was:

> I've never seen a calculator come up with the wrong answer when adding two numbers.

1.00000001 + 1 doesn't equal 2, therefore the claim is false.

Re: I’m worried that they put co-pilot in Excel

#226

Post by stavros »

sjsdaiuasgdia wrote: post #219
stavros wrote: post #185

Earlier quoted context omitted.

> Programs can be very close to 100% reliable when made well. This is a tautology. > I've never seen a calculator come up with the wrong answer when adding two numbers. https://imgz.org/i6XLg7Fz.png > And technically, most bugs are predictable in theory, they just aren't known ahead of time. When we're talking about reliability, it doesn't matter whether a thing can be reliable in theory, it matters whether it's reli…

RE: the calculator screenshot - it's still reliable because the same answer will be produced for the same inputs every time. And the behavior, though possibly confusing to the end user at times, is based on choices made in the design of the system (floating point vs integer representations, rounding/truncating behavior, etc). It's reliable deterministic logic all the way down.

> I've never seen a calculator come up with the wrong answer when adding two numbers.

1.00000001 + 1 doesn't equal 2, therefore the claim is false.

Re: I’m worried that they put co-pilot in Excel

#227

Post by yfontana »

ryandrake wrote: post #173
candiddevmike wrote: post #57

Earlier quoted context omitted.

I don't understand why generative AI gets a pass at constantly being wrong, but an average worker would be fired if they performed the same way. If a manager needed to constantly correct you or double check your work, you'd be out. Why are we lowering the bar for generative AI?

I've been trying to open my mind and "give AI a chance" lately. I spent all day yesterday struggling with Claude Code's utter incompetence. It behaves worse than any junior engineer I've ever worked with: - It says it's done when its code does not even work, sometimes when it does not even compile. - When asked to fix a bug, it confidently declares victory without actually having fixed the bug. - It gets into this mo…

> - It says it's done when its code does not even work, sometimes when it does not even compile.

> - When asked to fix a bug, it confidently declares victory without actually having fixed the bug.

You need to give it ways to validate its work. A junior dev will also give you code that doesn't compile or should have fixed a bug but doesn't if they don't actually compile the code and test that the bug is truly fixed.

Re: I’m worried that they put co-pilot in Excel

#229

Post by newscracker »

I feel what this article says based on some recent (non-catastrophic) experiences. I think I’m probably an above average user when it comes to Excel skills. I love spreadsheets. But I struggle with formulas like index, match, vlookup/xlookup and many others, and even more so when it requires nesting one within another and coming up with the underlying logic that leads to some complex nested formulas.

Over the past couple of months, I’ve tried some smaller models on duck.ai and also ChatGPT directly to create some columns and formulas for a specific purpose. I found that ChatGPT is a lot better than the “mini” models on duck.ai. But in all these cases, though these platforms seemed more capable than me and could make attempts to explain their formulas, they were many a times creating junk and “looping” back with formulas that didn’t really work. I had to point out the result (blank or some #REF or other error) multiple times and they would acknowledge that there’s an issue and provide a working formula. That wouldn’t work either!

I really love that these LLMs can sort of “understand” what I’m asking, break it down in English, and provide answers. But the end result has been an exercise in frustration and waste of time.

Initially I really thought and believed that LLMs could make Excel more approachable and easier to use — like you tell it what you want and it’ll figure it out and give the magic incantations (formulas). Now I don’t think we’re anywhere close to that if ChatGPT (which I presume powers Copilot as well) struggles and hallucinates so much. I personally don’t have much hope with the (comparatively) smaller and older models.

Re: I’m worried that they put co-pilot in Excel

#230

Post by buellerbueller »

Esophagus4 wrote: post #193
buellerbueller wrote: post #126

Earlier quoted context omitted.

Not every topic on HN needs a contrarian's hot take.

Well that wasn’t very nice. Do you have anything to say other than, “I don’t need to hear what you have to say”?

I think this repartee encapsulates a huge frustration with the tech sector:

> op (as legacy business): BAU

> you (as tech): disrupt! disrupt! disrupt!

> me: no thank you; that's not necessary

> you (as tech): stop being mean!

Not wanting your "disruption" is not being un-nice. Your disruption was not asked for in the first place. Forcing it (Uber, Doge, et. al.) on marketplaces, often illegally, and vacuuming it up the income ladder to the already-wealthy IS the "not nice" thing.

Post reply on HN