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

141–150 of 493 posts

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

#141

Post by simonw »

refulgentis wrote: post #139
virgildotcodes wrote: post #138

I really don't understand why anyone writing articles about ChatGPT uses 3.5. It's pretty misleading as to the results you can get out of (the best available version of) ChatGPT. For comparison, here are all the author's questions posed against GPT4: https://chat.openai.com/share/ed8695cf-132e-45f3-ad27-600da7...

It's a bit hard to use for most, either $20/month fixed for a limited # of messages, or you need to be able to reason through how to get an API key, or get another 3rd party service with similar cost & limits.

You can use GPT-4 for free via Bing - though I find it a little hard to explain to people how they can do that because I'm never sure what the rules are with regards to creating Microsoft accounts, whether you can use any browser or have to use Edge, what countries it's available in etc.

Actually maybe the recommendation should be to use GPT-4 for free via https://copilot.microsoft.com/ instead now.

(Except I can't tell which version of GPT that's using yet - there was a story on 5th December that said GPT-4 Turbo was "coming soon", not sure when "soon" is though: https://blogs.microsoft.com/blog/2023/12/05/celebrating-the-... )

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

#142

Post by tedunangst »

callalex wrote: post #131
boomboomsubban wrote: post #69

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…

I’m confused, you are searching for, specifically, a local phone number and you are upset that the machine interprets that as you looking for a local result? That’s what most people expect from a local number search. Perhaps the incorrect thing is not your internet search results, but actually your phone carrier for lying to you and telling you that a caller has a local number?

If I search for a ten digit number, it is not helpful to return a local business that shares the last four digits.

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

#143

Post by golol »

tentacleuno wrote: post #87
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.

> [...] but that also speaks for how hard evaluating search quality is. Would you be able to share some of your personal highlights regarding this? I've partially kept up-to-date with the DIY, non-corporate search space (YaCY and friends). I'd love to understand a bit more behind the engineering decisions made when creating a search engine; it seems like a very hard problem to solve. P.S. Marginalia is a very impress…

I just tested Mariginalia and it was completely unable to lead me to a Wikipedia or imdb page when searching for "driver ryan gosling" and variations. It just listed lots of random articles.

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

#144

Post by navjack27 »

ChrisArchitect wrote: post #62

Blah blah blah. Could you lay this article out any worse? What are the queries you used to test? I want to try them too. Buried in here somewhere. Using an adblocker is not expert anything. That you've defined your own opinion for what some of the results should be blows the thing up. Searching youtube downloader, many people would be fine with some of the ad covered but totally functional sites that pop up on Google…

Completely agree. I personally thought searching "Vancouver snow report" to be extremely strange. Just search zip code or city name and weather. Two words. That's all you need to get results. What the hell is snow report? Do you even think you can trust weather reports 10+ days out?

Whole article is rambling and silly and assuming.

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

#145

Post by D13Fd »

shados wrote: post #120
0x38B wrote: 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.

Yeah. At first I primarily used Kagi to move away from Google as a company, hoping for results that were equally good. But Google search actually feels crappy now in comparison.

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

#146

Post by xpressvideoz »

> However, there's a sizable group of vocal folks who claim that search results are still great.

I think that this very sentence shows the author's bias, because I feel that Google's search results are not just great, but better than what it was 10 years ago.

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

#147

Post by tedunangst »

virgildotcodes wrote: post #138

I really don't understand why anyone writing articles about ChatGPT uses 3.5. It's pretty misleading as to the results you can get out of (the best available version of) ChatGPT. For comparison, here are all the author's questions posed against GPT4: https://chat.openai.com/share/ed8695cf-132e-45f3-ad27-600da7...

Why does OpenAI continue to offer chatgpt 3.5 if it's so bad?

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

#148

Post by azinman2 »

tedunangst wrote: post #147
virgildotcodes wrote: post #138

I really don't understand why anyone writing articles about ChatGPT uses 3.5. It's pretty misleading as to the results you can get out of (the best available version of) ChatGPT. For comparison, here are all the author's questions posed against GPT4: https://chat.openai.com/share/ed8695cf-132e-45f3-ad27-600da7...

Why does OpenAI continue to offer chatgpt 3.5 if it's so bad?

Cheaper and faster.

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

#150

Post by realcertify »

xpressvideoz wrote: post #146

> However, there's a sizable group of vocal folks who claim that search results are still great. I think that this very sentence shows the author's bias, because I feel that Google's search results are not just great, but better than what it was 10 years ago.

You must be kidding, Google is becoming worse every day. Still better than useless Bing though.
Post reply on HN