Live data from Hacker News

Demo of =GPT3() as a spreadsheet feature

twitter.com

71–80 of 149 posts

Re: Demo of =GPT3() as a spreadsheet feature

#71

Earlier quoted context omitted.

A human developer once told me that bad data is better than no data. So of course a human developer made an AI that makes bad data.

FWIW, the actual saying is that for the purposes of collection by enemies (like Facebook and Google or KGB and NSA), the only thing better than no data is bad data.

FWIW, I was told that well before Facebook was a thought in the Zuck's head. Pre-socials, nobody shared data like is done today, so the NSA had to actually work to get it. Kids these days... /s

Re: Demo of =GPT3() as a spreadsheet feature

#72
post #13
post #11

The ability of language models to do zero-shot tasks like this is cool and all, but there is no way you should actually be doing something like this on data you care about. Like think about how much compute is going into trying to autofill a handful of zip codes, and you're still getting a bunch of them wrong.

Yeah, I think energy efficiency considerations will become important at some point. Or at least they should.

They only will if we price in the true cost of energy including negative externalities

Re: Demo of =GPT3() as a spreadsheet feature

#73
post #33

The amount of 90% sensible, 10% ridiculously wrong computer generated crap we’re about to send into real humans’ brains makes my head spin. There’s truly an awful AI Winter ahead and it consists of spending a substantial amount of your best brain cycles on figuring out whether a real person wrote that thing to you (and it’s worth figuring out what they meant in case of some weird wording) or it was a computer generat…

Idea: Use GPT-3 to identify GPT-3-generated snippets.

Then we need to train a model that gives us an idea of how accurate each prediction is

Re: Demo of =GPT3() as a spreadsheet feature

#74
post #5

From one of the replies: “This is awesome. I also love how 20% of the zip codes are wrong. Messy AI future seems really fun and chaotic.”

The author posted a follow up using a more advanced (and expensive) gpt3 model (davinci) which does a better job of parsing out the zip codes. It generally does a better job at everything, but if you can get away with one of the less expensive models then all the better.

Re: Demo of =GPT3() as a spreadsheet feature

#75
post #19

The amount of 90% sensible, 10% ridiculously wrong computer generated crap we’re about to send into real humans’ brains makes my head spin. There’s truly an awful AI Winter ahead and it consists of spending a substantial amount of your best brain cycles on figuring out whether a real person wrote that thing to you (and it’s worth figuring out what they meant in case of some weird wording) or it was a computer generat…

It depends on how people use the tools. For example the thank you note one -- if someone just prints off the output of this and sends it, yeah, that's bad. But if someone uses this to do 90% of the work and then just edits it to make it personal and sound like themselves, then it's just a great time saving tool. I mean, in this exact example, 70 years ago you'd have to hand address each thank you card by hand from sc…

I would classify that act of editing as "completing the remaining 10% of the work." Somebody has to do it, whether you're doing it from the writing side as in your example, or making the reader do it from their side, as in my grandparent comment's example. But it's usually the last 10% of anything that's the hardest, so if someone abdicates that to a machine and signs their name to it (claiming they said it, and taking responsibility for it) they're kind of an asshole, in both the schlemiel and the schlemozel senses of the word.

I could extrapolate in my extremely judgmental way that the person who does that probably has a grandiose sense of how valuable their own time is, first of all, and secondly an impractical and sheepishly obedient devotion to big weddings with guest-lists longer than the list of people they actually give a shit about. Increase efficiency in your life further upstream, by inviting fewer people! (Yeah right, might as well tell them to save money by shopping less and taking fewer trips. Like that would ever work!)

But I digress, and anyway don't take any of that too seriously, as 20 years ago I was saying the same kinds of things about mobile phones... like "Who do you think you are, a surgeon, with that phone?" Notice it's inherently a scarcity-based viewpoint, based on the previous however-many years when mobile phones really were the province only of doctors and the like. Now they're everywhere... So, bottom line, I think the thank-you notes are a lousy use of the tech, but just like the trivial discretionary conversations I hear people having on their mobile phones now that they're ubiquitous, this WILL be used for thank-you notes!

Re: Demo of =GPT3() as a spreadsheet feature

#76

51s -- "We are truly grateful", says the heartfelt thankyou card that was written by an algorithm in a spreadsheet.

The problem's worse than you know. I've heard that sometimes real humans who tell a lot of people "thank you" aren't even that thankful.

Re: Demo of =GPT3() as a spreadsheet feature

#78
post #77

The tasks on the first sheet is easily accomplished by flash fill in MS Excel and I suspect less prone to error. Not sure why flash fill is not more popular

What is flash fill? I have worked a lot on Excel sheets and still haven’t heard anything about it.

Re: Demo of =GPT3() as a spreadsheet feature

#79
post #33

The amount of 90% sensible, 10% ridiculously wrong computer generated crap we’re about to send into real humans’ brains makes my head spin. There’s truly an awful AI Winter ahead and it consists of spending a substantial amount of your best brain cycles on figuring out whether a real person wrote that thing to you (and it’s worth figuring out what they meant in case of some weird wording) or it was a computer generat…

Idea: Use GPT-3 to identify GPT-3-generated snippets.

Is that not sort of what a GAN is?

Re: Demo of =GPT3() as a spreadsheet feature

#80
post #11

The ability of language models to do zero-shot tasks like this is cool and all, but there is no way you should actually be doing something like this on data you care about. Like think about how much compute is going into trying to autofill a handful of zip codes, and you're still getting a bunch of them wrong.

Microsoft and Google both have excellent formulas for dates - and are getting there for addresses. Right now - the most useful things you can accomplish in sheets center around what the underlying models are good at - general inference and generation based on text. Anything needing exact outputs should be a numeric formula or programmatic.

Non-exact outputs are actually a feature and not a bug for other use cases - but this takes a bit of use to really see.

Post reply on HN