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

11–20 of 493 posts

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

#11

Post by marginalia_nu »

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.

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

#14

Post by arthurcolle »

I use serpapi for my hot RAG and the results are fine.

Brave search API is obscenely overpriced. I hope someone is working on Search because Google has become a singularly garbage company. Propping up DEI is sinful enough but just failing to compete is lame. /shrug

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

#16

Post by toomim »

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.

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

#17

Post by johnfn »

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.

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

#18

Post by jmclnx »

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.

To me it is only due to the ads, google and bing return nothing but ads on the first page. Plus for me to have the joy of seeing these ads, I need to got through a CAPTHA that I need to try multiple times.

But all in all, a very good article

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

#19

Post by charcircuit »

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…

>it's fully neural embeddings-based search. No keywords, only an embedding of what the actual content of a webpage is.

What prevents websites from gaming their embedding? Switching to a similarity search doesn't prevent the results from being gamed.

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

#20

Post by marcinzm »

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…

How is that different from keywords? Embeddings aren't magic, they're just page content. Content is trivial to game since it's controlled by the website owner.

edit: The results are also from my quick QA not that great. Searching for "what is the best mouse to buy" leads to links to buy random mice versus review summaries or online discussions on mice. One of the recommended queries of "Here is a great fun concert in San Francisco" leads to some really bizarre results in non-English languages that have nothing to do with either SF or concerts.

edit2: Also, Google has been using LLMs part of their search since at least 2018 so definitely not just keyword matching there.

Post reply on HN