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

131–140 of 493 posts

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

#131

Post by callalex »

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’m confused, you are searching for, specifically, a local phone number and you are upset that the machine interprets that as you looking for a local result? That’s what most people expect from a local number search.

Perhaps the incorrect thing is not your internet search results, but actually your phone carrier for lying to you and telling you that a caller has a local number?

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

#132

Post by lanstin »

ec109685 wrote: post #124
Nextgrid wrote: post #104

Earlier quoted context omitted.

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.

Google is a complex system so “want” can just include we are making money from the blog spam and while we don’t like it other things take priority over fighting it as effectively as we could.

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

#133

Post by naet »

I think the result grading is too opinionated here.

For example, the first query is "download YouTube videos", for which Google is ranked "terrible" for not showing you a command line open source program. But the literal first result is an ad supported site where I can paste in a YouTube link and download it right from the browser. That seems like exactly what most people would want or to the CLI tool the author is searching for. The author seemed to be looking for sites without ads as what they wanted to see in search results more than search relevance.

Search is a very gamed system with a lot of SEO spam type results, but I think a much better analysis could be done for more meaningful results. Also I recreated some of the searches and got very different results (including ublock origin in the top three responses). Again, a more scientific ranking system could help uncover better data on searches.

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

#134

Post by whakim »

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…

I really don't think that's true. For example, page 29 of your link describes "Lowest Quality Content." Most of the search results that the author rated as spammy or scammy clearly fit these guidelines, which means that either (1) the raters aren't knowledgeable enough about the subject matter to determine that the website they're rating is harmful or misleading; or (2) the raters are rating these sites correctly, but it still isn't having the desired effect.

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

#135

Post by jimmytucson »

ec109685 wrote: post #121
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.

> Why would an average user want blog spam search results?

I didn’t say they would :)

In fact, I can’t figure out how your comment relates to mine. Are you claiming that Google doesn’t factor blog spamminess into its evaluation of search results? If so, that’s quickly put to bed by the document I linked, pretty much section 4.6. Excerpt:

> Creating an abundance of content with little effort or originality with no editing or manual curation is often the defining attribute of spammy websites.

You could claim that they fail to capture some essential quality of “blog spamitude” or that they don’t weight it heavily enough in their eval but to say they just, like, don’t know about blogspam over there, is pretty far fetched IMO.

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

#136

Post by w-ll »

Nextgrid wrote: post #114
w-ll wrote: post #68

Earlier quoted context omitted.

i cant remember where i read this, but something about how google ranks site that have google ads higher than sites that dont. makese sense, its evil, but makes sense, thats why we get all this scrapped spam. is there any more info on this?

Intentionally ranking sites with Google ads higher would be a huge antitrust liability, so no way they're doing that. On the other hand, they can achieve virtually the same outcome while keeping plausible deniability by just not doing anything that would downrank sites with ads (of which a significant chunk is likely to be Google's). Spam sites often include ads.

i dont think they public disclose that fact

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

#137

Post by w-ll »

mixdup wrote: post #110
w-ll wrote: post #68

Earlier quoted context omitted.

i cant remember where i read this, but something about how google ranks site that have google ads higher than sites that dont. makese sense, its evil, but makes sense, thats why we get all this scrapped spam. is there any more info on this?

this is like focusing on one single problem as being the cause of the decline of the United States. It's actually a lot of things combining and there's not going to be one fix

wtf decline of the United States are you talking aboout

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

#138

Post by virgildotcodes »

I really don't understand why anyone writing articles about ChatGPT uses 3.5. It's pretty misleading as to the results you can get out of (the best available version of) ChatGPT.

For comparison, here are all the author's questions posed against GPT4:

https://chat.openai.com/share/ed8695cf-132e-45f3-ad27-600da7...

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

#139

Post by refulgentis »

virgildotcodes wrote: post #138

I really don't understand why anyone writing articles about ChatGPT uses 3.5. It's pretty misleading as to the results you can get out of (the best available version of) ChatGPT. For comparison, here are all the author's questions posed against GPT4: https://chat.openai.com/share/ed8695cf-132e-45f3-ad27-600da7...

It's a bit hard to use for most, either $20/month fixed for a limited # of messages, or you need to be able to reason through how to get an API key, or get another 3rd party service with similar cost & limits.

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

#140

Post by behnamoh »

alexforster wrote: post #116
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…

DDG is just repackaged Bing. Always has been. I remember looking into them when I was ready to job-hop many years ago, and they asked for dedication to their search engine as their foremost requirement for employment. It's the "drop-shipping" equivalent of search engines.

hope kagi takes ddg place in terms of adoption. never really liked ddg even though i always care about privacy.
Post reply on HN