Live data from Hacker News

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

danluu.com

111–120 of 493 posts

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

#112
Honestly, this is depressing. Back in the day, AltaVista and AskJeeves existed but returned terrible results, and Google showed up to disrupt them all. It seems like we should be on the verge of repeating this cycle.

Maybe LLMs will help, but I can’t shake the nagging feeling that the situation will simply get worse with LLMs, not better, due to hallucinations and the apparent “gullibility” of LLMs: I would not be surprised if SEOing an LLM turns out to be easier than SEOing Google.

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

#113
post #17

I noticed that the author uses ChatGPT3.5 rather than 4, which is a rather large difference. I don't have the knowledge to rerank all questions the author asked, but I will say that a test of ChatGPT 4 leads me directly to youtube-dl, which is better than every other search engine listed.

I’ve come to recognize that any article that uses 3.5 has an agenda.

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

#114
post #68
post #28

Earlier quoted context omitted.

Definitely more profitable not to. Especially as Google is an ad company, not a search company. I’d rather see a world with numerous paid/subscription search engines, that are motivated to do nothing but return search results well. I expect you would see some of the SEO crap getting solved.

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.

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

#115
post #26

I have recently started using kagi after seeing a recommendation here. From what I understand, it aggregates results from multiple sources rather than having their own indexer. The results aren’t really any better, but the lack of ads and videos in the results makes for a cleaner experience. I also haven’t yet taken advantage of the extra features to block certain websites from results. Personally, I pay the $5 mostl…

Pretty sure the reason Kagi is better isn't because they use multiple sources, it's just because they can use the presence of ads as a negative ranking signal, something that none of the major public search engines will ever do as it goes against their own business model.

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

#116

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.

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

#117
post #16

Do search engines censor political topics these days? If you search "truthsocial" on ddg, the truthsocial.com website is the first hit. But if you search "trump truthsocial", it doesn't give you trump's truthsocial page, and doesn't even give you truthsocial.com within the first few pages of search results. Since ddg uses bing, does anyone know what is happening here at bing? It looks like google results are similar.

I have concluded that Google definitely censors search results relating to the Ukraine war, after vainly searching for articles about documented Ukrainian war crimes (reported in mainstream Western media like NYT/WaPo).

I'm not seeing this. I Googled "war crimes by ukrainian soldiers" and the top link was an Amnesty International Article, "Ukraine: Ukrainian fighting tactics endanger civilians".

https://www.amnesty.org/en/latest/news/2022/08/ukraine-ukrai...

I use Google as little as possible because I don't like surveillance advertising but fair is fair.

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

#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 out a query’s meaning(s), judging the user’s intent (were they looking for some specific answer, etc.), evaluating the “quality” of a website, rating the site’s usefulness in relation to the query’s meaning/intent, etc.

All this is to say, it’s not that search companies don’t do exactly what the author did here, it’s just that they have different standards than the author. And I’d venture their standards match their users’ better than the author’s, but maybe not or not forever, anyway.

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

#119

I am not sure what the intention of this post is. In my handpicked results Kagi far outperforms Marginalia. #1 "Gordon ramsey" (misspelled "Gordon Ramsay"). Marginalia shows "The Life I Imagine: are my cheeks red?". Kagi corrects to Gordon Ramsay and shows relevant results. #2 "Ukraine war". Marginalia shows an article about the Russian Orthodox church and a Substack post about the war. Kagi shows Wikipedia, Al Jazee…

It seems to me that the name "marginalia" is not just a random set of syllables. It sounds like it's doing what it says on the tin, which is gooder than not doing what it says on the tin. (distinct from whether what it says on the tin is something you want)

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

#120
post #94

Re: Kagi, I heard about it on HN, tried it for 100 searches, then subscribed. When I search for random JS and CSS things, MDN is the first result, and if it isn't, I can downrank whatever spammy site(s) are on top. --- I wish I had a local LLM trained to detect clickbait and or low-effort content. I imagine searching YouTube and having all the clickbait collapsed together (just like Kagi condenses listicles), with th…

I became a huge fan of Kagi after seeing it on hacker news too. It's amazing how good a search engine can be when it's not full of ads.
Post reply on HN