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

Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

danluu.com

Post reply on HN
Print view View original

121–130 of 493 posts

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#121

Post by ec109685 »

jimmytucson wrote: post #118

If you wanna know why Google (or any search engine) sucks, just look at how it measures its own search results. Most search companies do this “at scale” according to very specific guidelines, like what the author did here but on steroids. For example, take a look at Google’s 168-page instruction manual for search quality raters: https://static.googleusercontent.com/media/guidelines.raterh... It talks about figuring o…

Why would an average user want blog spam search results?

My hope is as LLM’s improve, they can be more discriminating about the results returned.

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#122

Post by bpodgursky »

boomboomsubban wrote: post #69

Can someone tell me why Bing, and thus DDG, has switched to prioritizing local results? I'll search the most inane things, like lyrics to a song, and get results for local businesses containing maybe one word in common. It's most frustrating with phone numbers. I picked up the habit of searching the random numbers that called me, to try and find out if they were possibly important. I used to get a bunch of spam sites…

I suspect it's a failure to distinguish mobile searches (where people are legitimately looking for a business) from desktop searches.

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#123

Post by ChrisArchitect »

SnazzyJeff wrote: post #66
ChrisArchitect wrote: post #62

Blah blah blah. Could you lay this article out any worse? What are the queries you used to test? I want to try them too. Buried in here somewhere. Using an adblocker is not expert anything. That you've defined your own opinion for what some of the results should be blows the thing up. Searching youtube downloader, many people would be fine with some of the ad covered but totally functional sites that pop up on Google…

> Download firefox? What's that? All the top links are fine? No one's looking at the 7th listing for a simple query to download a program. They are if the first six results are SEO bullshit. Which is the de-facto state of affairs for Google today: advertising traipsing around as search.

heh, they're not. They're all variations of mozilla download pages and site posts.

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#124

Post by ec109685 »

Nextgrid wrote: post #104
Renaud wrote: post #31

Earlier quoted context omitted.

Subscription model like Kagi seems to work pretty well against gaming the results. Their only remaining incentive is to be good enough that people keep paying for the service.

It works not because they're somehow smarter or have more resources than Google at detecting spam/SEO, it's because unlike Google (and other ad-supported search engines), they make money from result quality and have an interest in blocking spam. Google on the other hand makes money off ads (whether on the search results page itself or on the spam sites), so spam sites are at best considered neutral and at worst consi…

Kagi works because there is no incentive for SEO manipulators to target it since their market share is so small.

Super tinfoil hat to believe Google wants to send users to blog spam websites (e.g. beneficial to Google).

Anytime there is money to be made, there is an effectively infinite amount of people trying to game the system.

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#125

Post by dvngnt_ »

boomboomsubban wrote: post #69

Can someone tell me why Bing, and thus DDG, has switched to prioritizing local results? I'll search the most inane things, like lyrics to a song, and get results for local businesses containing maybe one word in common. It's most frustrating with phone numbers. I picked up the habit of searching the random numbers that called me, to try and find out if they were possibly important. I used to get a bunch of spam sites…

you can use true person search for numbers

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#126

Post by ec109685 »

jeffreyw128 wrote: post #10

The issue with traditional search engines is that keyword-first algorithms are extremely gameable. Try https://search.metaphor.systems - it's fully neural embeddings-based search. No keywords, only an embedding of what the actual content of a webpage is. So in the mentioned example of searching for Youtube downloaders, with Metaphor you'll get only Youtube downloaders ( https://search.metaphor.systems/search?q=This%2…

https://getthatvideo.com/ Is the first result for downloading YouTube videos. Seems super sus (especially since the site doesn’t load).

Auto-prompted to: "Here's a helpful website for downloading YouTube videos:"

Also, this result is horrible:

“What does it mean if someone is not covered in nfl football?”

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#127

Post by zihotki »

Libcat99 wrote: post #7
coldcode wrote: post #3

Search was the biggest feature of the web in the early '00s. Now it's such a mess. I can't imagine Search will ever be amazing again, given all the complexity of providing quality while still avoiding all the crap.

Is it actually more complex to provide good results, or is it just more profitable not to? I have a hard time believing an organization like Google doesn't have the resources to provide a search engine that's just as usable as what they had 6 years ago (around the time I feel like the decay really set in). Seems a lot more likely that it's just more profitable to serve up garbage sponsored content.

Google, or Alphabet, is not a search emgine company. It's an ads company and that's what they are optimizing for.

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#128

Post by throwawaaarrgh »

Search engines are not designed to give you the information you desire. They are designed to sell ads or metadata. "Result quality" is of no consequence.

If you actually wanted accurate results you wouldn't use a tool that is literally attempting to read your mind like a fortune teller. It is impossible to know what you want just by the word "snow". Jesus Christ engineers are so dumb.

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#129

Post by Brian_K_White »

zzleeper wrote: post #105

For me the problem is not just that searching on Google is bad, but that sometimes it COMPLETELY hides exactly what I'm looking, for no good reason. For instance, I wrote an R ggplot2 package called "fedplot" (following the convention of calling the package for the figure style it replicates, as in "bbplot" for BBC-style charts). Try searching for it on Google: "github" "fedplot" doesn't get you anywhere. Meanwhile,…

Their black box semantic guesser has been told not to feed the radicalizing conspiracy theorist fires about federal plots.

Who needs to know anything about government owned land anyway?

Re: Compare Google, Bing, Marginalia, Kagi, Mwmbl, and ChatGPT

#130

Post by whakim »

Renaud wrote: post #31
kristopolous wrote: post #24

Earlier quoted context omitted.

I'm a big fan of the non commercial site search engines because of the gaming aspect. If you're not generating revenue from the clicks the game mostly goes away. I'm not saying people aren't entitled to make some money, but it clearly incentivizes user hostile behavior. Maybe make it an option because legitimate sites like journalism also use this model.

Subscription model like Kagi seems to work pretty well against gaming the results. Their only remaining incentive is to be good enough that people keep paying for the service.

But the author tried Kagi and the results don't appear to be noticeably different, filled with scammy adspam just like Google and Bing. Kagi's results seem to mostly aggregate existing search engines [1], so this isn't much of a surprise. Perhaps a subscription-based service that operates an index at Google's scale might help, but no such thing exists to my knowledge.

[1] https://help.kagi.com/kagi/search-details/search-sources.htm...

Post reply on HN