Maybe

It's a legal requirement when your car hits 80085 that you must take a photo, it supersedes all other laws.

Are you kidding? Microsoft has always been shit at math. According to Microsoft Excel, 2 + 2 = 12:04 AM Jan 1, 1900.

Integers are days in Excel, no? So I think 2+2= 12:00 AM Jan 5, 1900.

Yeah, it's like complaining that a hammer isn't good at turning a screw. There's a whole trend of Chess content creators featuring games against ChatGPT where it forgets the position or plays illegal moves, and it just doesn't mean anything. ChatGPT was never designed or intended to be able to evaluate a chess position, and incidentally, we do have computer programs that do exactly that and have been better than any human player since the 1990s. So what is even the point?

And what you could do is to enable an LLM to use these tools and reason about their outcome. Complaining that an LLM isn’t good at adding numbers is like complaining that humans aren’t as fast as calculators when multiplying large numbers.

What, you don't always work with 16 digit numbers that are automatically truncated? What could go wrong? We don't use 16 digit numbers for anything, really./

It's hard to believe that's still a thing but it is!

seeking explicit compatibility with Lotus

I need a shower.

I'm talking about using it when you're "not great at Excel", not when "you can't do basic math".

Always verify the results given to you by LLMs.

I think you're completely missing the point here.

I'm not great at Excel. That doesn't mean I can't do basic math, it means I struggle designing an xlookup or hlookup.

If AI does that for me, I'll be a happy bunny. And then run a dozen different iterations of data to verify that the results I'm getting are correct.

This is what this integration is for - it's not a replacement for a human brain, it's an assistant. As are all LLMs.

it's not a replacement for a human brain, it's an assistant.

This is what I think AI and automation is generally good at and should be used for - mitigating unpleasant or repetitive work so that the focus of the user is productivity/creativity.

This is what this integration is for - it's not a replacement for a human brain, it's an assistant. As are all LLMs.

The context is something we disagree on wholeheartedly. Those funding and fundraising for AI and an enormous subset of those using are not looking to use AI in the way we are talking about. The prior are hoping to use AI to extract value from it at the expense of people who would otherwise need to be paid, or they and claim it can do anything and everything. Those using it, many of them, do not have a sufficient understanding to comprehend the solution. They are basically "vibe coding". Tell the LLM to do something they aren't knowledgeable about, then keep telling it to fix the problems until they don't see problems anymore. Yes, spreadsheet formulas are likely simpler than an app but I know people who use AI for Google Sheets and they rarely test any results, let alone rigorously.

Anecdotal, sure, but I don't have enough faith in humanity to presume everyone else is doing something wildly different.

Edit: To expand, LLMs specifically, are what I consider to be the worst side of "AI". You can use ML and neural networks to create "AI" (self altering, alien blackbox algorithms) to become proficient in analyzing information and solving problems. LLMs create a situation where the model appears intelligent because it knows how to mimic language... and so now we pretend like it can do whatever people can do.

Well... Yeah, I get what you mean, and - in general - I agree.

However, to me it's also a bit like criticising the use of hammers because a lot of idiots hit themselves on the heads with them. Or, even worse, hit others on the heads.

AI/LLMs are a tool, and just like any other tool, they can be misused. That doesn't mean the tool is bad, or immoral, or whatever, to use.

That's why I hate the today's discourse of "anything that has AI is shite be default" that so many people online have.

Let's laugh at obviously bullshit attempt of shoving AI down consumer's throats, but when it comes to actual, proper implementation - like in the case of baking Copilot into Excel - it becomes yet another optional tool at users' disposal.