Live data from Hacker News

Shirt Without Stripes

github.com

201–210 of 639 posts

Re: Shirt Without Stripes

#201

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.

I disagree, "shirt without stripes" is an unusual word choice, not one that our ML models would be optimized for. Try "solid color shirt" and you'll see how much better the results are - at least on Google.

> "shirt without stripes" is an unusual word choice

Lol what? These are words a toddler would understand.

Re: Shirt Without Stripes

#202
post #13

The point of this isn't asking how to apply boolean search operators, it's showing that the largest AI-focused companies in the world absolutely suck at NLP.

Why would you really apply NLP to a search engine though? Generally speaking a weighted keyword search is good enough 95% of the time and requires significantly less resources to perform.

5% revenue sales and revenue increase? Why indeed!

Re: Shirt Without Stripes

#203
post #81

My Operating Systems professor (Tomasz Jordan Kruk, PhD) in college had an appropriate anecdote for this: "Humans usually don't intuitively understand the word 'no'. Please imagine a non-pink elephant."

Maybe you mean, "Please don't imagine a pink elephant." Imagining a non-pink elephant seems pretty easy.

If the first thing that comes to your mind when you hear "imagine a non-pink elephant" isn't either a pink elephant or "WTF, how is a pink elephant?", then you are in a very small minority.

Re: Shirt Without Stripes

#204

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…

That was when people built websites to deliver content. Now people build websites to get highly ranked in Google. No matter how good google's algos are, they can't win when the underlying content is just SEO'd garbage.

SEO'd garbage often contains ads, including Google ads. There's no incentive for Google to fix this problem.

Google's job is not to give you great search results, it's to keep you clicking on ads. Ideally it would be the ads on the search results page directly, but if that doesn't work then a blogspam website with Google ads is the next best thing.

If Google was a paid service this problem would be solved the next day. Oh, and Pinterest would completely disappear from Google too. :)

Re: Shirt Without Stripes

#206

This comment would go from "unreadable" to "interesting" if you had phrased it as: "Vaguely similar to a joke from _the movie_ Ninotchka that _the Slovenian philosopher_ Zizek often uses...." Give people context. Don't assume people know what you know.

Man you couldn't be more condescending if you tried. 1. Capital letters indicate proper nouns so syntactically it's clear Ninotchka is the name of something and Zizek is someone's name. 2. You contributed this wholly worthless comment using a device that has access to more information than any other in the history of the world. Are you also one of those people that asks people define words for you instead of looking…

The GP didn't come across as ill-intended to me; it outlined an issue, gave a solution, and hopefully everyone who viewed it thought about context for half a second. I do agree with it that adding context to the comment is better than assuming random readers are going to actually look up capitalized names.

Your comment, on the other hand, comes off as the one that's disparaging and includes a personal attack.

Re: Shirt Without Stripes

#207

This is a good example of the bar HNers must have these days when they bafflingly assert that Google is somehow getting worse from what they remember. Google has gotten better, it's just HNer expectations that have changed as they expect more and more magic. For example, the subtitle on the repo is "Stupid AI" when this query has never worked in these search engines, and it won't anytime soon. You'd think the technic…

> has never worked in these search engines

I would expect there to be an e-commerce site or blog post somewhere containing a page with the exact title "shirts without stripes" and I'd expect it to be the first match.

Re: Shirt Without Stripes

#208
post #162

Earlier quoted context omitted.

Because you want to sell shirts without stripes to customers who want them.

I expect most users genuinely looking for such a product would just search "plain shirt"

Apple probably expected most users genuinely wanting to make a phone call would hold their iphone 4s a certain way. Turns out expectations don't always match reality.

Re: Shirt Without Stripes

#209

Google Photo's search is a similar source of amusement for me. While it's quite good, it also fails fairly regularly and sometimes amusingly. For me "turtle" includes understandable mistakes like fish, a snail, and a rock that does look a bit like a turtle. However "turtle" also includes this, a picture of sequined slippers reflecting light?! https://i.imgur.com/4aSlA4B.jpg I'm guessing one of those reflections looks…

I can almost see the left slipper looking kinda like a head of a turtle

Re: Shirt Without Stripes

#210
Since I was a teenager, if someone energetically asserts a statement is “true” or “false,” I drop the true or false and evaluate the statement. In essence, their only communication to me is, ‘I think this is important!’ Often, why they think it’s important is more pressing than whether the statement is true.
Post reply on HN