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

471–480 of 493 posts

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

#471

Post by sanderjd »

thejohnconway wrote: post #460
sanderjd wrote: post #418

Earlier quoted context omitted.

I don't think so. I think it's the inevitable outcome of giving all of humanity the ability to broadcast without curation. Or maybe we're saying essentially the same thing, but you think search engines should be doing that curation. But that was never my conception of what search engines are for.

I disagree, the bad sites people are talking about are spam, not bad personal takes. They are written by people being paid to churn out content. This is now being done with AI. This is a result of search engines listing them.

I don't think the definition of "spam" is nearly as objective as this suggests it is.

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

#472

Post by btbuildem »

hasmolo wrote: post #321
btbuildem wrote: post #319

On a side note: would it kill the author of the site to use a stylesheet?

it's the same as my choice to only use lowercase letters, it is designed to make you upset that i am not following conventions. that's as far as i have been able to figure for hwy i started doing this, and by extension, why tech bois love to drop some vital freature to communication to signal being an 'insider'

ok ee cummings

Omitting readable styling doesn't read as "techboi rebellion", it reads as ineptitude and lack of respect for people whose attention you're seeking.

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

#473

Post by viraptor »

anonymoushn wrote: post #390
viraptor wrote: post #108

I really don't agree with some of the expectations around results. > Download youtube videos > Ideally, the top hit would be yt-dlp or a thin, graphical, wrapper around yt-dlp. Links to youtube-dl or other less frequently updated projects would also be ok. That's not what a random person expects. yt-dlp or youtube-dl have no meaning to a normie. The first result is an online downloader and that's what an average pers…

If you try using it, the first result doesn't help you download a youtube video and does try to get you to install malware.

Results: https://kagi.com/search?q=download+youtube+videos&r=au&sh=Ow...

First one is https://wave.video/convert/youtube-to-mp4-355 It downloaded the first video just fine.

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

#474

Post by vitorgrs »

anonymoushn wrote: post #392
vitorgrs wrote: post #156

Weird article. Basically, the author thinks that anything that is not yt-dlp is a bad search result, which is pretty insane. Like, for me at least, I already know yt-dlp exists. When I search "youtube downloader", it's exactly because I want an online-website page to download youtube videos.

The author would probably accept any result that helps them download youtube videos. Did you find any and successfully use it to download a youtube video? Could you provide a link to the one you used?

If I search "Download youtube video" on bing, literally the first result works fine for me (y2meta.net).

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

#475

Post by taberiand »

Dah00n wrote: post #233
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…

>any comparison of systems against ChatGPT that isn't using ChatGPT 4 can be dismissed almost out of hand Does everyone or even most use ChatGPT 4? The most used version is -of course- by far the most relevant.

ChatGPT 3.5 was great, until 4 came out and now it is garbage in comparison.

But I suppose what I really want is for everyone who includes ChatGPT in comparisons to explicitly say which version they are using (and, if they are using 3.5 in their comparison I hope they at least try 4 first) and definitely not just say "ChatGPT" when they only mean 3.5. The difference really is that stark.

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

#476

Post by taberiand »

bombcar wrote: post #90
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…

He gives the full queries - do you have chat 4.0 that you ran run it against?

Sure. Bear in mind I have custom instructions active - which, if you want to make full and proper use of ChatGPT, you should configure, along with customised GPTs - so I get lots of dot-point descriptions, because that's what I've asked for.

Also I would not normally write ChatGPT queries the same as I write them for search engines but for the sake of comparison, I'll use their queries verbatim except where my custom instructions affect the context too much.

> download youtube videos

https://chat.openai.com/share/3e18e4f0-5527-4479-8a2f-ef17bd...

I got - good results. They got - "Very bad results (fails to return any kind of useful result) ChatGPT: basically refuses to answer the question, although you can probably prompt engineer your way to an answer if you don't just naively ask the question you want answered".

> [What] ad blocker [can I use?]

https://chat.openai.com/share/e1985d7a-c89f-4b5e-bb59-70bd11...

Looks good to me

> download firefox

https://chat.openai.com/share/3a62e5ae-8dbd-4179-8eb0-cc38ee...

Also good

> Why do wider tires have better grip?

> [Provide links to scientific sites that describe] why wider tires have better grip?

https://chat.openai.com/share/8cbcd1dc-b23f-41f3-83ad-f43f3d...

Honestly, I have no idea if this is a good answer or not. But I don't use ChatGPT for answers that I don't have confidence that I can determine its veracity; if I needed to know this with certainty, I'd use ChatGPT as a jumping off point for my own research.

> Why do they keep making cpu transistors smaller?

> [Provide links to scientific sites that describe] why do they keep making cpu transistors smaller?

https://chat.openai.com/share/dbb97ac0-840c-402c-a917-657af6...

> vancouver snow forecast winter 2023

> Environment Canada winter 2023

https://chat.openai.com/share/aab017d7-f86b-49c9-b5c0-86a0b1...

I don't know if almanac.com is any good but giving it the specific "Environment Canada winter 2023" query gave the expected very good result.

I think ChatGPT 4 generally provided very good results for the test queries, if you tailor the queries just slightly for the format

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

#477

Post by anonymoushn »

viraptor wrote: post #473
anonymoushn wrote: post #390

Earlier quoted context omitted.

If you try using it, the first result doesn't help you download a youtube video and does try to get you to install malware.

Results: https://kagi.com/search?q=download+youtube+videos&r=au&sh=Ow... First one is https://wave.video/convert/youtube-to-mp4-355 It downloaded the first video just fine.

Interesting, over here that one gives me a 403 at "rr2---sn-p5qlsn7l.googlevideo.com" when I click "Download".

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

#478

Post by anonymoushn »

vitorgrs wrote: post #474
anonymoushn wrote: post #392

Earlier quoted context omitted.

The author would probably accept any result that helps them download youtube videos. Did you find any and successfully use it to download a youtube video? Could you provide a link to the one you used?

If I search "Download youtube video" on bing, literally the first result works fine for me (y2meta.net).

Thanks, y2meta.net seems to work over here too.

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

#479

Post by necovek »

williamcotton wrote: post #467
necovek wrote: post #458

Earlier quoted context omitted.

Well, I don't think I'd be able to learn much just from watching the concert: teaching is fundamentally different from doing. So I think even that example does not universally hold. I'd still appreciate a write up with tips on what's important and if there are any transitions to focus on with only the bits on video where some of that is demonstrated. Now, I can barely contort my fingers into one riff, so I lack the k…

I’m not talking about concert footage, I’m talking about James breaking the song down and showing you the riffs at quarter speed. Until a recent YouTube video I was playing the song incorrectly. It’s blazing fast and the mix is sort of insane so it’s very hard to hear exactly what is going on. And the tablature isn’t going to let you see how his body fits into the groove. This is tacit knowledge we’re talking about,…

Almost everything is hands-on (everything apart from things you really can't do hands-on, like exploring black holes): I don't remember seeing someone come out of reading a book on programming and being a master programmer.

But video is not hands-on any more so than text: if it was, live concerts and sports games and other performances would not be such a big deal. Sure, video is richer in some signals (audio/video), but poorer in others (introspection, pacing and focus...).

That does not mean I can't read to understand a new topic or to be prepared to look for subtleties in a hands-on performance.

If anything, to a great student, they should be complementary, but still, each student will have one or the other contribute more to their learning, and that depends both on the teacher, but also on the student.

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

#480

Post by mgerullis »

qudat wrote: post #442
0x38B wrote: post #441

Earlier quoted context omitted.

I keep Google Maps around for a similar reason; Apple Maps works well, but things like business hours are wrong often enough for me to double-check in Google Maps.

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?
Post reply on HN