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

Privacy Pass Authentication for Kagi Search

blog.kagi.com

Post reply on HN
Print view View original

121–130 of 359 posts

Re: Privacy Pass Authentication for Kagi Search

#121

Post by abound »

echoangle wrote: post #112
abound wrote: post #107

Earlier quoted context omitted.

There's no auth required at this stage of the handshake, so you can test from any number of devices/locations/networks/etc and confirm you get the same value. We could publish it, but it will change every epoch/month. Plus, if you don't trust the service to not issue special key pairs to track you, you probably won't trust us to not do the same when publishing the key material. There are schemes involving third-parti…

Makes sense in general, but to make sure I understand it: > Plus, if you don't trust the service to not issue special key pairs to track you, you probably won't trust us to not do the same publishing the key material. You could publish it on some sort of blockchain to make sure it can’t be changed and is public for everyone, right? > A malicious server could maintain separate key pairs for users it wanted to track, b…

> You could publish it on some sort of blockchain to make sure it can’t be changed and is public for everyone, right?

Your understanding is correct, that's definitely something we could do. It is also something anyone else could do to keep us honest :)

Re: Privacy Pass Authentication for Kagi Search

#122

Post by autoexec »

jjice wrote: post #105
autoexec wrote: post #85

Earlier quoted context omitted.

As the user of a service things like payment overhead, a small userbase, and dev salaries aren't my problem. My only concern is what I'm getting for what I'm paying. $5 a month for fewer than 10 searches a day is clearly not a good deal. $10 a month might be worth it for some, but an extra $15 a month on top of that for AI results is kind of crazy.

That extra $15 a month is for access to LLMs. They currently support the Claudes, the GPTs (not o1), Mistral, Gemini, Llamma, Qwen QWQ, Nova, and DeepSeek. It's currently unlimited access in the standard chat format. You can also choose if you want the chat to RAG search results into the context for additional info, and then cite those sources. To me, replacing a Claude/ChatGPT subscription with $15 on top of a compa…

That makes a lot more sense!

Re: Privacy Pass Authentication for Kagi Search

#123

Post by esafak »

perdomon wrote: post #119

Can someone make a case for Kagi? I'm using Google + Claude for all my websearch needs. I don't feel like there's a gap there, but maybe that's because I've never experienced anything better and can't imagine it? I do value privacy, but I wouldn't pay extra for more private search results. I might pay extra for __better__ search results, but that's hard to measure. Just curious if anyone has had a legitimately great…

If you don't immediately notice the difference between Kagi's and Google's results, Kagi is not for you.

Re: Privacy Pass Authentication for Kagi Search

#124

Post by prophesi »

mortar wrote: post #82
alexwebb2 wrote: post #70

Earlier quoted context omitted.

I think the idea here is that it literally can't be traced to the user – at no point is there anything passed that would allow Kagi to make the association between the user and the query.

Thanks, yes completely agree! I guess the part I’m concerned with is the politically side whereby they could be potentially compelled to change the method slightly after the fact and be forced to slip something in somewhere in a quite technical process now making it possible. I’d love to assume this will never happen, I’m just concerned that even if it did I’d never find out - Because unfortunately the more popular t…

The best that we can do is to continue working on FOSS solutions that make it technically impossible to backdoor. I haven't grok'd the protocol yet, but it seems to claim you only have to trust the client. The client is open source, so it would be hard for it to be backdoor'd without the community noticing.

Cryptography is a literal godsend for people living under oppressive regimes.

Re: Privacy Pass Authentication for Kagi Search

#125

Post by trvr »

esafak wrote: post #123
perdomon wrote: post #119

Can someone make a case for Kagi? I'm using Google + Claude for all my websearch needs. I don't feel like there's a gap there, but maybe that's because I've never experienced anything better and can't imagine it? I do value privacy, but I wouldn't pay extra for more private search results. I might pay extra for __better__ search results, but that's hard to measure. Just curious if anyone has had a legitimately great…

If you don't immediately notice the difference between Kagi's and Google's results, Kagi is not for you.

This is so true. I've been on Kagi since March 2024. On the occasion that I find myself on Google on someone else's computer, I find it completely unusable from a search result perspective. It's all just junk. Kagi has me as a paying customer forever.

Re: Privacy Pass Authentication for Kagi Search

#126

Post by mayneack »

perdomon wrote: post #119

Can someone make a case for Kagi? I'm using Google + Claude for all my websearch needs. I don't feel like there's a gap there, but maybe that's because I've never experienced anything better and can't imagine it? I do value privacy, but I wouldn't pay extra for more private search results. I might pay extra for __better__ search results, but that's hard to measure. Just curious if anyone has had a legitimately great…

For me the killer kagi feature is that I can manually up and down weight domains in results. I can "pin" and always get wikipedia results or "block" and never get pintrest or raise or lower as needed. Brave search has a similar feature, but they only seem to support "block" not "lower", which is what I use a lot more often.

https://kagi.com/stats?stat=leaderboard

Re: Privacy Pass Authentication for Kagi Search

#127

Post by Klaus23 »

drdaeman wrote: post #28

Neat! It's rare to see that a service you use actually does something that benefits the user rather that itself. An unexpected, but a really pleasant surprise. I wish this extension would integrate better with the browser by automatically understanding the context. That is, if I'm in a "regular" mode it'll use my session, but if I'm in a "private browsing" mode (`browser.extension.inIncognitoContext`) it'll use Priva…

The downside of this is that if you are not on a larger network, the IP address will probably deanonymise you. Kagi knows you are logged in, and if you open a private browsing window to do a spicy search, they could link the searches. Fast switching between modes is undesirable.

Re: Privacy Pass Authentication for Kagi Search

#128

Post by furyofantares »

perdomon wrote: post #119

Can someone make a case for Kagi? I'm using Google + Claude for all my websearch needs. I don't feel like there's a gap there, but maybe that's because I've never experienced anything better and can't imagine it? I do value privacy, but I wouldn't pay extra for more private search results. I might pay extra for __better__ search results, but that's hard to measure. Just curious if anyone has had a legitimately great…

If you can't imagine a gap then I think it might not be for you.

I tried kagi after finally getting sick of some of my google results. Kagi was able to deliver on some of those results.

It's not like, shockingly better results. I do think they're better on average, but I'm not sure.

However, in the cases where I couldn't find what I was looking for on google and could on kagi, well, that's a binary result. I'll take the success and not the failure.

I was surprised by how much better I found the UI. That's actually the thing that sold me on the subscription to begin with. Going in, I would not have expected UI to sell me on such a thing.

I have since customized it somewhat; there are sites I usually really like results from and they are upranked, and sites I don't care for which are downranked. I've felt like this has lead to even better experience, but I haven't gone back to google to compare.

Re: Privacy Pass Authentication for Kagi Search

#129

Post by cmehdy »

perdomon wrote: post #119

Can someone make a case for Kagi? I'm using Google + Claude for all my websearch needs. I don't feel like there's a gap there, but maybe that's because I've never experienced anything better and can't imagine it? I do value privacy, but I wouldn't pay extra for more private search results. I might pay extra for __better__ search results, but that's hard to measure. Just curious if anyone has had a legitimately great…

Auto filter for sources, downrank sources you dislike, sort results by recency, have an engine that actually respects what country or language you're trying to search into, and finally present results visually the way you want them. It's worth trying to use it actively for a month or so, and you'll see if you need it or not. I would not to back to google even if Google paid me.

Re: Privacy Pass Authentication for Kagi Search

#130

Post by mulderc »

perdomon wrote: post #119

Can someone make a case for Kagi? I'm using Google + Claude for all my websearch needs. I don't feel like there's a gap there, but maybe that's because I've never experienced anything better and can't imagine it? I do value privacy, but I wouldn't pay extra for more private search results. I might pay extra for __better__ search results, but that's hard to measure. Just curious if anyone has had a legitimately great…

For me, Kagi felt like a godsend as my Google searches had become polluted, and I had to dig way deeper in the search results to get anything decent. They also have an AI assistant that gives you access to all the major AI models and integrates with their search in a way that I have found very useful.

I would recommend at least giving it a try to see if you notice a difference. For my job, the monthly fee more than pays for itself

Post reply on HN