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

481–490 of 493 posts

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

#481

Post by mgerullis »

bambax wrote: post #207

I'm in the camp of those who think Google's results are still very good. I admit I use adblock (uBlock Origin) and won't even try to disable it. I understand the author's point of turning off their ad blocker "to get the non-expert browsing experience" but then they could make a different test with uBlock on for every query and see how it goes. It's also a bit inconsistent to expect results for downloading videos men…

Yeah, author seems to heavily underestimate his own needs vs general needs. But for what Google et al know about me the results could indeed be more precise. I have developed a habit of appending “GitHub” in the search query for when I am actually looking for source code vs just trying to find a page that just downloads me a video.

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

#482

Post by bayindirh »

_benj wrote: post #374
cratermoon wrote: post #361

Earlier quoted context omitted.

Did anyone notice that Kagi showed as barely better than Google in the article?

Yeah, for the the results of kagi are so much better than anything else, that it makes me wonder how objective can one be measuring search results. I use google in a clients computer and it’s just horrible. But it could also be a factor of the customizations I’ve made for my kagi. Ban quick a few paywalls sites, always put Wikipedia articles on top, prefer blogs than stackoverflow stuff…

Even without customization, I did not change anything yet, Kagi provides far superior results to Google.

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

#483

Post by Dah00n »

anonymoushn wrote: post #415
Dah00n wrote: post #227

Earlier quoted context omitted.

I get savefrom.net in both Incognito and normal tabs, uBlock or not. I have no idea why you get crap results that are somehow different. uBlock doesn't change google results in Firefox for me at all. It seems you get crap added , not removed.

savefrom.net is a crap result.

You seem to be missing the point of the discussion here, which was to compare results returned. Not to rate if one site is better than another.

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

#484

Post by Dah00n »

zzleeper wrote: post #437
Dah00n wrote: post #238

Earlier quoted context omitted.

Searching for "fedplot" looking for https://github.com/sergiocorreia in the results: Qwant: Result 1 Bing: Result 1 Google: Result 2 Marginalia: Zero results ChatGPT 3.5: Some Federal Reserve dot plot nonsense and no useful results.

I would say Google has zero results, as it does not find https://github.com/sergiocorreia/fedplot nor https://sergiocorreia.github.io/fedplot/ ; even with the advantage of the latter being manually added to the Google Admin console. Meanwhile, both Bing and Qwant give me exactly what I want

I don't know what customization or personalization is going on in your search compared to mine, but I followed GPs directions and posted my results. Searching today (this time not in Incognito and with extensions turned on in Firefox), I see the correct result as number 1 on google.com, so one better than last time.

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

#485

Post by scarface_74 »

someguy5281 wrote: post #450
marginalia_nu wrote: post #11

While I've made huge improvements to the algo recently, I do think Marginalia Search got a bit lucky with the sample queries, as it is still IMO far more hit and miss than many alternatives, but that also speaks for how hard evaluating search quality is. Its efficacy is also strongly dependent on understanding that it's a keyword search engine with no semantic understanding.

> Its efficacy is also strongly dependent on understanding that it's a keyword search engine with no semantic understanding. Good. I love keyword search. "Semantic understanding" can be so biased and ... just shady sometimes.

Keyword search leads to things like every website would put meaningless words in the meta section of their website so it would be picked by Altavista

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

#486

Post by kipchak »

Torkel wrote: post #448
algas wrote: post #439

Earlier quoted context omitted.

That first result re: tires is simply wrong. Wider tires don't have a larger contact patch; the size of the contact patch is determined by the weight of the car and the air pressure in the tires: A = W / P So the reason wider tires improve handling is more complex and subtle. Also, FTA: Assuming a baseline of a moderately wide tire for the wheel size. - Scaling both of these to make both wider than the OEM tire (but…

So, why is it? Such a nerd snipe this one. 400+ comments and still could not get the answer.

As a partial explanation, maybe it's not the case that area = weight/tire pressure as an absolute rule? In which case we get back to the layman knowledge of "wider tires have a greater contact area."

As an extreme example, run flats at atmospheric tire pressure don't drastically change their area.

https://web.archive.org/web/20090327161537/http://performanc...

From https://www.6speedonline.com/forums/996-turbo-gt2/242759-imp...

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

#487

Post by s3p »

mgerullis wrote: post #480
qudat wrote: post #442

Earlier quoted context omitted.

Yep, same. Yelp is not nearly as good in Apple Maps but for in town directions it works great for me.

You use yelp for directions?

No for business info. Apple pulls directly from Yelp. issue is when you want more info or you want to get a closer look at the business and tap any of its images, it will take you straight to the app store to download Yelp.

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

#488

Post by chupapimunyenyo »

scarface_74 wrote: post #485
someguy5281 wrote: post #450

Earlier quoted context omitted.

> Its efficacy is also strongly dependent on understanding that it's a keyword search engine with no semantic understanding. Good. I love keyword search. "Semantic understanding" can be so biased and ... just shady sometimes.

Keyword search leads to things like every website would put meaningless words in the meta section of their website so it would be picked by Altavista

No, if it's done right. Source: I made my own search engine

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

#489

Post by KomoD »

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…

> with Metaphor you'll get only Youtube downloaders

I clicked into the top 5 results, none of them were real youtube downloaders that worked, so I clicked the next 5 results, then I finally got one single (really slow) downloader that worked. 1 out of 10 top results

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

#490

Post by pythux »

nsagent wrote: post #411
binarymax wrote: post #399

Earlier quoted context omitted.

Long time DDG user (>10 years) here, and it’s astounding to me that they haven’t prioritized making their own independent index to switch off Bing. I would have expected them to do it like 5 years ago, but there’s afaik no initiative to do so. It’s unfortunate and am now trying other engines like Brave search.

I also occasionally try Brave search when a DDG search fails. Sometimes Brave finds what I want, but I frequently get Captcha (and now proof of work) challenges that are quite annoying. I don't get this with any other search provider (though StartPage would frequently do this a while back). I hope this is just a phase, because I would likely use Brave Search more if not for this issue.

Hi, Brave engineer here,

Are you by any chance using a VPN while using Brave Search? (ProtonVPN?)

Thanks for your help, we're working on ways to reduce the number of captchas shown to VPN users and your feedback is very useful.

Post reply on HN