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

Shirt Without Stripes

github.com

Post reply on HN
Print view View original

441–450 of 639 posts

Re: Shirt Without Stripes

#441

Post by mkl »

jedberg wrote: post #394
holler wrote: post #313

Earlier quoted context omitted.

I've noticed this too, and frequently wonder why there aren't new and better search startups...

There are, like DuckDuckGo. But the first complaint is usually "their results aren't as good as Google" and that's because Google in reality still gives better results because of their (lack of) privacy. People want better results but don't want to be tracked, and those things are in opposition to each other.

IME DuckDuckGo has all the same problems people are talking about here. I uses DDG as my primary search engine.

Re: Shirt Without Stripes

#442

Post by joshspankit »

pbhjpbhj wrote: post #417
joshspankit wrote: post #342

Earlier quoted context omitted.

Yes, you have points, but they break down here: “Shirt -stripes” is unambiguous to a system, yet the first result on Amazon(.ca) is a striped shirt, and the 3rd is sweatpants.

As someone else said you don't know that's wrong for what Amazon are optimising. If they find people [with your background profile] who buy shirts are susceptible to buying sweatpants, they might also find that if the seed you with "sweatpants" as an idea up front that the repeated presentation of sweatpants in "people who bought X also bought Y" sections is more effective. That's the sort of thing I'd expect Amazon…

Like, when was the last time this was considered ideal?

“Yes, I would like an unstriped dress shirt please”

“How about this striped shirt?”

“No thank you, I would like an unstriped dress shirt please”

“I have some lovely jogging pants”

“Ok, I need to be clear here, I would like a dress shirt that has no stripes”

“Can I interest you in a white undershirt? People who buy dress shirts usually buy undershirts”

....

Re: Shirt Without Stripes

#443

Post by belorn »

Alex3917 wrote: post #212
rgovostes wrote: post #23

The point that the author is making, in a very understated way, is that all three companies have PR websites that breathlessly describe their advanced AI capabilities, yet they cannot understand a very simple query that young children can.

At least this is relatively innocuous. Until recently if you did a Google Image Search for "person" or "people", it only showed white men.

One can play this game a lot and most results will return expected cultural biased results. A "kind person" is apparently a white girl. A "good person", a white woman. A "bad person", white men. A "evil person", white men. A "honest person", equal mix of white women and white men. "Dishonest person", white men in suits. "Generous person", hands of white women. "Happy person", women of color. "Unhappy person", old white men. "Criminal person", Hispanic men. "Insane person", white men. "Sane person", white women.

Is it surprising that very few of the result surprises me?

Re: Shirt Without Stripes

#444

Post by pbhjpbhj »

jedberg wrote: post #390
bartread wrote: post #221

Earlier quoted context omitted.

I couldn't quite believe your comment when I read it so I did a Google image search for "person" and the results weren't a lot better than you'd suggested. Mostly white men, a few white women, a very few black women, a handful of Asians, and multiple instances of Terry Crews. The net result of that Google search, combined with the "Shirt Without Stripes" repo, leaves me even more unimpressed with the capabilities of…

If you really want to be disappointed, search for [doctor] and [nurse]. Unless things have really changed, [doctor] will be mostly white men and [nurse] will be mostly white and Filipino women. But don't blame the AI. The AI has no morality. It simply reflects and amplifies the morality of the data it was given. And in this case the data is the entirety of human knowledge that Google knows about. So really you can't…

All the young doctors are women. 13 women to 12 men.

Nurses it's 34 women to 5 men. Proportions of skin tones are what I'd expect to see in a city in my country.

Re: Shirt Without Stripes

#445

Post by hammock »

gnulinux wrote: post #412
hammock wrote: post #374

Earlier quoted context omitted.

Why is it hard? Honestly. Add a "t" to "no" and you get a basic Boolean query.

Boolean queries aren't statistically analyzed; they're parsed and algebraically evaluate. So your point seems to support the opposite thing you're supporting.

Yeah I don't really know how github works. When I click the OP link I see a tiny bit of text and then three screenshots. Is there a whole article on this topic I'm missing?

Re: Shirt Without Stripes

#446

Post by zerd »

pbhjpbhj wrote: post #414
animalCrax0rz wrote: post #259

Earlier quoted context omitted.

"there is no evidence of cancer" and "there is evidence of no cancer" are two different statements with different meaning, so it's more complex a task than just understanding the importance of "no" in a sentence. It's involves semantic analysis of the sentence. The paper I linked to below describes a technique they call "deep parsing." Check it out for more context.

Lexical analysis is surely clever enough to make "no evidence" and "no cancer" the atoms used and should even differentiate "no cancer" from "no, cancer" pretty easily? Are we really still at 80s chatbot level functionality when it comes to string parsing? Related aside: It frustrates me no end that spellcheck still doesn't appear to use any probablistic considerations, like Markov chains, to determine the intended w…

The general problem is much harder than that. You need to understand double negatives, when do they invert the meaning and when do they underline it? "Ain't nobody got time for that" can be interpreted in different ways. And then you need to understand sarcasm. Then a later sentence can invert the meaning of an earlier one. E.g. "This is the best movie ever. Said no one". Using word-pairs as features is easy, but there are just so many exceptions and ambiguity it's a very difficult problem to solve well.

Re: Shirt Without Stripes

#447

Post by conanbatt »

DenisM wrote: post #197

This problem is known as "attribution" - you have a "no" or "without" in the sentence, but you don't know where it belongs. One could (and one does) argue that the problem cannot be solved with statistical methods (ML), especially not in any domain where accuracy is required, such as medical recored analysis: "no evidence of cancer" and "evidence of no cancer" are very different things. Zooming out, the language fiel…

Believing this is a problem of attribution, I would expect to see results that are shirts without stripes, or not-shirts with stripes.

If it just disregards the word without, well, that's pretty bad.

Re: Shirt Without Stripes

#448

Post by kator »

Joe: "Hey is Lisa back from vacation?"

Larry: "I saw a red Lamborghini in the parking lot!"

Most people will assume Lisa is driving a red Lamborghini and back from Vacation, meanwhile, all the bots are searching for Lamborghini vacations and trying to figure out what's going on in the conversation.

Re: Shirt Without Stripes

#449

Post by pbhjpbhj »

floatingatoll wrote: post #273
seiferteric wrote: post #137

I have noticed in the past few years google results have become noticeable worse for similar reasons. Google used to _surprise_ me with how good it was able to understand what I was really looking for even when I put in vague terms. I remember being shocked on several occasions when putting in half remembered sentences, lyrics, expressions from something I had heard years ago and it being the first! result. I almost…

Google was good at launch because it was harvesting data from webrings and directories to provide it "high quality" link ranking data. However, they didn't thank or credit or share any of their revenue with the sites whose human curation helped their results become so impressive. Seeing that Google search was effective, most human curators stopped curating directories and webrings. The SEO industry picked up the slac…

Google was good because they used to optimise to giving the best search results, that was their aim. Now their aim is best profit, it seems, and their results appear to correspond (keep you on site longer).

Re: Shirt Without Stripes

#450

Post by pbhjpbhj »

jedberg wrote: post #394
holler wrote: post #313

Earlier quoted context omitted.

I've noticed this too, and frequently wonder why there aren't new and better search startups...

There are, like DuckDuckGo. But the first complaint is usually "their results aren't as good as Google" and that's because Google in reality still gives better results because of their (lack of) privacy. People want better results but don't want to be tracked, and those things are in opposition to each other.

It took me something like 6 years, but I've gone over to DDG. Their results were poorer than Google's for me, so when I tried to switch I used to end up repeating and adding !g to every search. I don't think DDG got better, but Google results are bad enough that I think they're equal in quality now (for me). I don't login to Google, have tracking disabled, use uBlock and pihole; FF/Brave.
Post reply on HN