Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Kagi added a setting for removing paywalled links from search results

kagi.com

Post reply on HN
Print view View original

331–340 of 421 posts

Re: Kagi added a setting for removing paywalled links from search results

#331

Post by rcpt »

m463 wrote: post #269
rcpt wrote: post #203

Earlier quoted context omitted.

Micropayments never work. It's too much friction for the median user to decide if they want to spend a quarter on an article. https://nakamotoinstitute.org/library/micropayments-and-ment...

Used to be you would trade a yak or a horse for something. Then you could trade little pieces of metal. In the future, why not something smaller? I mean, people are trading virtual things (like an app). Why not something small for something as small as a website view?

Look at the paper. There's a floor to mental work. Even if it's a nickel, having to make that decision is enough friction to kill the whole deal

Re: Kagi added a setting for removing paywalled links from search results

#332

Post by TeriyakiBomb »

I love Kagi. I want to see them do well, of all of the search alternatives, this is the only one where I’ve never felt the need to go back to google.

I was setting a up a new computer the other day and got confused that the first three links for a search were ads, then I remembered it was google and they hide the things you’re looking for.

Site priority, lenses and the slop filter are all icing on the cake.

Re: Kagi added a setting for removing paywalled links from search results

#333

Post by Jtarii »

sarjann wrote: post #47
SamBam wrote: post #5

Hmmm, so if you are looking for some news item, you'll only find AI-written clickbait articles covered in pop-up ads, rather than any news sites that employ journalists?

That's why it's a choice. If you weren't going to sign up to a site then it's just a pure degradation of experience to see links you can't use.

you can generally just bypass paywalls via archive sites.

Re: Kagi added a setting for removing paywalled links from search results

#334

Post by TeriyakiBomb »

CoffeeOnWrite wrote: post #118
delis-thumbs-7e wrote: post #59

I think this is amazing. Love Kagi. I’m happy to pay for a good search. Nobody speaks about their AI Assistant, but it is really good. They somehow harnessed it so that it mainly searches info first and sticks to the verifiable data. I prefer it to Claude or any other, because it actually answers the question I need without fluff or “Great question! Here’s some plausible nonsense you can trip over instead of doing ac…

My household is hooked on the AI Assistant. It’s heartwarming to be able to buy consumer software that just works. If only Kagi had a Shopping feature, then it would be a complete solution for us.

Yeah, I’d like this too. It’s one of the only things I still miss from Google.

Re: Kagi added a setting for removing paywalled links from search results

#335

Post by natios »

bitpush wrote: post #281
cosmic_cheese wrote: post #91

Earlier quoted context omitted.

Right. I don’t mind paying when the value is clear and I feel like my time has been respected, and paywalled link showing up in search violates the second of those two. In most of the circumstances when those show up in my search I’m looking for information for immediate use and I am not going whip out a credit card. If I run into a paywall, I’m immediately hitting the back button and moving on to the next result, so…

This sounds a bit odd to me. When I'm hungry, I dont run to McDonald's and expect to be fed for free . I whip out my card, pay for the items, patiently wait for the food to be arrive and then eat. You could very well argue that why are you making me wait for my food when I'm hungry. What gives?

i think the crux here is you can’t get the food for free next door like you can get with information

Re: Kagi added a setting for removing paywalled links from search results

#336

Post by ymolodtsov »

carlosjobim wrote: post #125
ymolodtsov wrote: post #107

Earlier quoted context omitted.

The problem with micropayments isn't the tech really, it's that only the users want them but not any publisher. Which is completely reasonable.

Publishers want them and many have tried. It is the other way around, people don't want to make micro payments. Some say they do, but the evidence proves they're wrong. Edit: Typo

Why would any publisher want them? Who exactly tried?

As a publisher, I'd want consistent subscription revenue. The goal is to convince users to pay after they hit the paywall several times.

Re: Kagi added a setting for removing paywalled links from search results

#337

Post by notatoad »

preg_match wrote: post #188
frereubu wrote: post #96

The one thing I find slightly grating about links to Kagi blogs is the top comments are almost always "I use Kagi and it's great!" rather than about the content of the blog. And I'm a happy Kagi subscriber! I get that this is an option, but what it really shows to me is how broken the model for journalism is. In my view you almost always only get good-quality journalism if you pay for it. (Somehow - e.g. the BBC is p…

The biggest problem with micropayments is how credit card payment processors work. You typically pay a percentage fee. But they thought of everything, so you also pay a flat fee per transaction like 10 cents. So they can get their money from tiny transaction. So for something like a 20 cent micropayment, you pay more to your processor than you pocket. One solution is a universal token system or something like it. You…

Lots of smart people have tried to implement micropayments like this, and it has never worked.

Publishers would rather have the chance at $10 than give up the chance at $10 for 10c. And readers don’t want to be thinking about their credit balance every time they read an article.

Re: Kagi added a setting for removing paywalled links from search results

#338

Post by kelnos »

delis-thumbs-7e wrote: post #59

I think this is amazing. Love Kagi. I’m happy to pay for a good search. Nobody speaks about their AI Assistant, but it is really good. They somehow harnessed it so that it mainly searches info first and sticks to the verifiable data. I prefer it to Claude or any other, because it actually answers the question I need without fluff or “Great question! Here’s some plausible nonsense you can trip over instead of doing ac…

> They somehow harnessed it so that it mainly searches info first and sticks to the verifiable data.

I like this too, but it isn't as bulletproof as it sounds. I've run into two instances in the past week where it confidently gave me wrong information, because it ran into a search result that had wrong information, and it trusted that information.

You could perhaps say that's fine; if you were doing the search yourself, you'd get the same results and might trust the wrong information too. But the "might" there is... oh boy, I'm gonna say it... load-bearing: someone is much more likely to believe the confident LLM response than if they were looking directly at the primary source, along with search results with other sources that might contradict it.

Re: Kagi added a setting for removing paywalled links from search results

#339

Post by preg_match »

paweladamczuk wrote: post #270
preg_match wrote: post #185

Earlier quoted context omitted.

Keyword trustworthy, I think Kagi is one of the only companies that would be in a position to do this without pushback. But, regular models and harnesses work okay for this too. You just have to specify “web search”, very important.

Care to share your setup? I use pi and librechat and I am really limited by the lack of proper web connector. Testing Tavily right now, Kagi is next. I wonder why I see so few comments about it on HN, does everybody have this figured out already? Am I a dummy? Am I severely overstating how important of a frature web access and search is for LLM use?

I use Claude code for basically everything, since the harness is pretty complete. The online chat interface works fine too. For basic research I downgrade the model and effort. Smarter models are good at knowing when to web search rather than guess, but you should always specify “do a web search”.

The one caveat is opus has an absolutely awful voice. The way it writes is annoying and verbose. Sonnet actually works better for this type of thing.

Post reply on HN