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

401–410 of 493 posts

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

#401

Post by nvm0n2 »

SV_BubbleTime wrote: post #316
sanderjd wrote: post #306

Earlier quoted context omitted.

> It's the closest we can easily get to the 'average user experience'. Maybe it's the closest we can get (though I doubt it), but it definitely isn't close enough to tell us anything about the "average user experience". The average user has been using google for years, without taking any steps to avoid personalization. An incognito session (on a browser / machine / network that is probably fingerprinted...) is pretty…

Why are you assuming all users are logged in to google all the time?

Google has billions of user accounts ....

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

#402

Post by marginalia_nu »

ta988 wrote: post #375
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.

Just my feedback after trying to finally get to what it is exactly. I tried to find marginalia on DDG, not on the first page. Google has it after some garbage. If I go to marginalia.nu I get a SSL error. search.marginalia.nu works If i search on marginalia for duckduckgo there first link is somewhat relevant but is about the app, all the other links are related to DDG but of curious relevance. If I search for ublackl…

Hmm, what's your browser? I renewed the cert today... Only thing I can think of is that it might not like a wildcard cert for the bare marginalia.nu domain.

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

#403

Post by HarHarVeryFunny »

teleforce wrote: post #236
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…

I'm also in the same camp who think search results from Google is very good but ChatGPT based search with RAG is better, granted it's a paid version. The latter however is kind of experimental, personally would love to have another column on ChatGPT with RAG (Bing) and the fact the author ignored RAG is rather strange.

If you like Bing (ChatGPT with RAG), then also give perplexity.ai a try - similar concept, but IMO better executed.

https://www.perplexity.ai/

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

#404

Post by justinl33 »

> It's common to criticize ChatGPT for its hallucinations and, while I don't think that's unfair, as we noted in this 2015, pre-LLM post on AI, I find this general class of criticism to be overrated in that humans and traditional computer systems make the exact same mistakes.

Finally some one said it. We are unnecessarily harsh on hallucinations. LLM’s don’t intentionally ‘lie’. To say this is a wrongful anthropomorphism.

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

#405

Post by krapp »

justinl33 wrote: post #404

> It's common to criticize ChatGPT for its hallucinations and, while I don't think that's unfair, as we noted in this 2015, pre-LLM post on AI, I find this general class of criticism to be overrated in that humans and traditional computer systems make the exact same mistakes. Finally some one said it. We are unnecessarily harsh on hallucinations. LLM’s don’t intentionally ‘lie’. To say this is a wrongful anthropomorp…

It's also a wrongful anthropomorphism to claim that human beings "make the exact same mistakes" as LLMs, because they don't. Humans don't confabulate the way LLMs do unless they have a severe mental illness. A human doctor isn't as likely to simply make up diseases, or symptoms, or medications, whereas an LLM will do so routinely, because they don't understand anything like human anatomy, disease, chemistry or medicine, only the stochastic matching of text tokens.

We're not unnecessarily harsh on hallucinations, it's absolutely necessary because of how effective LLMs are at convincing people that because they can generate language, they are capable of sentient thought, self-awareness and reason. Acting as if humans and LLMs are basically equally trustworthy, or worse, that LLMs are more trustworthy, is dangerous. If we accept this as axiomatic, shit will break and people will die.

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

#406

Post by maronato »

justinl33 wrote: post #404

> It's common to criticize ChatGPT for its hallucinations and, while I don't think that's unfair, as we noted in this 2015, pre-LLM post on AI, I find this general class of criticism to be overrated in that humans and traditional computer systems make the exact same mistakes. Finally some one said it. We are unnecessarily harsh on hallucinations. LLM’s don’t intentionally ‘lie’. To say this is a wrongful anthropomorp…

To validate hallucinations is anthropomorphism. Tools shouldn’t make stuff up.

I don’t second guess Pythons math results. If the result is wrong, that’s my fault for coding it wrong, never Pythons for hallucinating

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

#407

Post by eep_social »

48864w6ui wrote: post #363
dpkirchner wrote: post #330

Earlier quoted context omitted.

The web has gotten bad because of what big search engines have encouraged. If they stopped incentivizing publishing complete garbage (by ruthlessly delisting low quality sites regardless of their ad quantity, etc) then maybe we'd see a resurgence of good content.

The web is bad because it is both popular and commercial. Every now and then I fantasize that just finding a sufficiently user-hostile corner would suffice to recreate the early internet experience of an online world nearly exclusively populated by anticommercial geeks.

I understand this is the tactic the Gemeni folks are using.

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

#408

Post by taberiand »

vitaflo wrote: post #338
taberiand wrote: post #61

Earlier quoted context omitted.

That was the first thing I checked reading the article. Although the argument would be 3.5 is free - any comparison of systems against ChatGPT that isn't using ChatGPT 4 can be dismissed almost out of hand; there is not much point talking about ChatGPT if it's not using ChatGPT 4 and making proper use of its capabilities. That is not to say that there aren't valid criticisms of and shortcomings in ChatGPT 4 - just th…

This is silly, most people aren't going to pay for ChatGPT, just like they won't pay for Google or DDG. So using 3.5 in this case is perfectly acceptable when we're talking about free software.

Kagi isn't free, that's on the list

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

#409

Post by ta988 »

marginalia_nu wrote: post #402
ta988 wrote: post #375

Earlier quoted context omitted.

Just my feedback after trying to finally get to what it is exactly. I tried to find marginalia on DDG, not on the first page. Google has it after some garbage. If I go to marginalia.nu I get a SSL error. search.marginalia.nu works If i search on marginalia for duckduckgo there first link is somewhat relevant but is about the app, all the other links are related to DDG but of curious relevance. If I search for ublackl…

Hmm, what's your browser? I renewed the cert today... Only thing I can think of is that it might not like a wildcard cert for the bare marginalia.nu domain.

Firefox android

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

#410

Post by acdha »

darkwater wrote: post #203
motoxpro wrote: post #195

This makes so much sense why people think search results are bad. Great results for "Download youtube videos" is "Ideally, the top hit would be yt-dlp or a thin, graphical, wrapper around yt-dlp" Just give me a website where I can plug in the DL link and download it to my hard drive. I don't care what package they are using (I don't worry about malware like I did in the 90s). 99.999% of people are not programming tin…

Malware or well, the actual viruses, in the '90s were a joke, especially because a computer was an isolated thing. Connected computers were the exception.

In the early 90s, yes. By the turn of the century the current industry we see today existed in basic form: malware stole credit cards, compromised PCs were used to send spam as part of botnets, etc. The only major advance was when cryptocurrencies made it much easier to launder money and the professionalism went up accordingly.
Post reply on HN