Imagine DuckDuckGo but with no ads and good results every time instead of 90% of the time… absolute game changer.

[1] https://github.com/searxng/searxng

The fact that I pay for search or email (proton) is not a proof that the companies are not doing something in secret, but it is somewhat necessary in the trust calculus that I am paying for a specific service to end up getting that service (that is to say, ad free, and not intentionally biased search results).

No need to cast shade on others who aren't like you.

My favorite feature is Smallweb [0]. I've actually replaced doomscrolling with browsing random personal blogs and discovering interesting corners of the internet.

[0] https://kagi.com/smallweb/

That said I’ve had a hard time getting other people on board. Apparently many people are just numb to the enshittification of the web?

Am I searching for the range of input voltages an Arduino can safely handle? Kagi.

Even people working close to us seem to have no conception of the economics of the web. Kagi is, practically speaking, an activist's service. Most people only respond to direct incentives. It's how we got to where we are now. I would expect this uphill battle almost naturally at this point.

- Really high SNR when searching about topics I am not a subject matter expert on.

- Really good at finding prior art on a topic while not necessarily limited to papers conferences and patents (e.g. finding obscure blog posts on a hobby project that actually is relevant prior work).

Arguably this can be achieved with frontier models but my experience is that Kagi is vastly more exhaustive and well I don't need to ask for references because they are indexed in the search itself.

Many of my Kagi searches never actually show me a Kagi interface before I get to the page that I want. Many of my search queries are putting something like "jj @gh !" in my browsers URL bar, which will navigate directly to https://github.com/jj-vcs/jj, or "nats @dh !" to navigate to https://hub.docker.com/_/nats/, etc. The ! will navigate directly to the first result, and the @gh will add site:github.com to your query.

I really liked the AI search, but it burns through credits too quickly. I have since switched to using Hermes, it's not quite as good yet, but it's a fraction of the cost.

I liked the idea of ad free, slop free search. There were some problems with that though, which were hard to push past. I really like being able to search for stores and local restaurants. Maps integrations were hit or miss, mostly miss. It was also weirdly slow for me, even to load the search page without a query.

Final point was their published and then unpublished support of Yandex. The CEO tried to argue some "search without borders" BS, but really they are taking your money that and sending some of it to a Russian company which is either directly or indirectly funding a pointless war. I took issue with that and remembered it every single time I opened the page. In particular it really didn't sit well with me that the response was flippant and then they took down their list of sources.

I've switched to DDG and have been happier, YMMV.

If you're looking for something more typical of search + AI, DDG is probably the next best. If you're looking for a search assistant that will find you a direct link to the leaked gta 6 footage that people are talking about or to summarise a comparison of 2 oss libs, Hermes is probably the one you're after.

The ai credit thing is real too and I’ve written to them about it several time. My solution was just to sign up for the entire year in one go

You have to keep in mind it’s only like $25 of usage, though they could handle the experience better. In the past in the assistant it would even delete your prompt when you ran out and it was super annoying

As a product though I think it’s great - more than good enough to get off of google, I like the privacy aspect, and it’s ai features slot in nicely between search and my Claude subscription

If you follow the money, somewhere you’ll find something unsavory. This is me mostly coping, admittedly, but Kagi is good enough that a) I want to cope and b) hope continues to thrive as a full featured search engine that is a legitimate alternative to Google

DDG is good too, not quite on par with Kagi though. Kagi is super configurable and customizable- e.g. lenses, down ranking websites (e.g. for me Pinterest appears way low in search results, ai slop detection etc)

It’s also cool to be a paying customer - you email them, they respond, and sometimes even fix a bug right away for you

Happy overall with the service even though I agree it’s not perfect

Couldn't you make the same argument about American companies such as DuckDuckGo?

Remember their “early adopter” drama? Wasn’t their only drama.

EDIT: Also technically Russia is in Europe ;)

Also, news.pravda.com publishes only the Truth in the English language. It's the Russian equivalent of Truth.social, which of course exclusively publishes the Truth. It's in the name, don't you see.

Ps. I just found out there is website called Pravda.social.

The Biden administration and western leaders chose monetary and logistical assistance with which Ukraine has fought Russia to a stalemate. That's not a terrible outcome if the alternative is Russia actually following through with their mad man nonsense.

Oh yeah, and winning isn't accomplished with overwhelming force. The West marching into Moscow was never a possibility, despite what Alex Dugin will have you believe. Winning is Putin backing down, being deposed, or doing the swan lake thing.

The liar is named Afghanistan.

> I won't ever forgive the west for throwing ukraine under the bus to express their anxiety about russia

What does this even mean?

> Russia will just replace him with someone on the right wing of russian politics. That's actually a worse scenario in every way.

Amazing. Russian voters will look at their economy, their dead, their global image, and choose someone even more inclined to continue the five+ year SMO.

I'm not so sure the succession will be smooth though. If anyone was equipped to seamlessly take the reins they'd be a threat to the current guy. Any internal struggle means less commitment to the war.

> The only victory path is to collapse russia. We have no way to do that and there are no domestic pressures indicating this will happen any time soon. And in every way Russia is hurting, Ukraine is suffering harder.

Don't need Russia to collapse, just need it to decide there are more important uses of their fighting-age men and money. Putin is committed, others need not be. Economically, things will continue to decline for Russians and while it's possible to fake it by printing money, reality eventually catches up.

> they swallowed their own cold war bullshit

You're thinking of the actual cold warrior. The one who worked in the soviet intelligence services and became a dictator. The one who initiated the invasion.

> Ukraine was just the nearest opportunity to do so, even if it meant fucking over 25 million people for no clear benefit.

When the US... rolled tanks into Ukraine? You're approaching self-parody my man.

And besides the small win this week things are still looking really bleak internationally.

I still use US services too much tbh but slowly things are improving.

I won't bore you with the details, but I fully believe he only ran for president in '24 because it was his only way to avoid prison. He was staring at two slam dunk convictions and his only outs were fleeing the country or taking over the department prosecuting him.

And even if he were to somehow circumvent the Constitution and fool the electorate that has, just this week, overwhelmingly told him he sucks, he's still not the dictator/mob boss that Putin has been for 30 years. He aspires to be that but Americans just aren't Russians.

> things are still looking really bleak internationally.

Yeah, it kind of sucks when the hegemon becomes this dumb hydra of isolationism, extortion, and military adventurism. Europe is doing a solid job of insulating itself from its mercurial western ally, I hope things will return to normal before too long.

There are options. Uruky is a great European search engine where you can use an European search index (EUSP) alongside other smaller ones. Their entire stack is USA free.

Wait til you realize the search engines you use now are funding directly AND indirectly even more pointless wars than that one...

Afaik DDG sources from bing and their own indexing.

https://orionbrowser.com

I wish they would. The extension works well for me most of the time, but every once in a while I end up on Ecosia and I’m confused for 2 seconds.

> For example, searching Kagi for !w Monty Python will search Wikipedia directly for "Monty Python" and take you to that Wikipedia search result. [1]

If you're on a plan with limited searches per month, it does not count against your quota.

DuckDuckGo has bangs as well.

[1] https://help.kagi.com/kagi/features/bangs.html

1. Navigation makes pointless detours.

2. The "rotate the map back to north-up" button doesn't work.

3. "You're looking at Barcelona and asked for restaurants? I know a few, in Tokyo"

4. Half of navigation window is useless UI elements I cannot hide.

I've been trying mapy.cz for a while because they were fantastic for tourism purposes, but they're locking more and more features behind a paywall and I'm not sure I want to pay for that. The killer features of Google Maps are the POIs, reviews, photos, Street View, and public transport planning. I cannot really switch to another map app without having those.

I guess the biggest problem is and will always be the quality of data. The reason I can't use CoMaps much is because OSM just doesn't have the same accuracy and recency of data on businesses and POIs in my area as compared to Google/Apple.

1. Transit. I'm in NYC, and Google Maps does a great job of showing the MTA, trains and busses. Every route, all the stations, which trains stop there and when, even where the entrances are. Kagi Maps has no train routes or layers. There's stations, most of them at least, but it's basically the Wikipedia entry for that station. No up-to-date info or routes.

2. Mobile apps. At least half of the time, my maps use is an Android intent for address or directions, which only an app can answer. And the only really good way to get your location and see what's around you.

I don't really notice latency at all personally, but fixing those things might bring my Kagi Maps usage from 0% to like 50%+.

I know, it's probably a pain in the butt to integrate with the transit systems of hundreds of cities for up-to-date info, but OSM does at least have the stations and routes. Not much point trying to beat the official MTA app in functionality, but something is better than nothing.

It's also weirdly hard to get to. Why isn't it an option in the main list of Kagi things? To get there from the Kagi homepage, I have to click on search options, then maps.

1) navigation

2) give me more info about this business that I tapped on

3) reviews; find related businesses, yelp style

I cannot figure out how to do any of those things with your UI.

Ideally, for (1), it’d let me choose to open in organic maps (reliably works at all) or apple maps (better when it works, which is rare offline, even with offline maps turned on) on my phone.

This might he fantasy land, but if it could send the location to BMW’s app, then that’d be awesome too. (The bmw app can send the location on to my car.)

(Not OP)

OP in the linked thread wanted to boycott Russia and Russian businesses. The “context” is that Kagi gives money to Yandex.

The answer from them : we are unimpressed by world politics.

Man… they are on my short list now.

"The moment 'politics' becomes a factor in search results is the moment I stop working on a search engine."

I'm having a very hard time equating what's happening in Ukraine to "politics", as if we're talking about the next election or something...

"Yandex represents about 2% of our total costs and is only one of dozens of sources we use."

So it should be easy to cut then. It's literally an argument for removing it, not for keeping it. God.

Most of us have the comfort of living in a place where bombs and missiles do not fall on our heads.

But not all of us. Some of us live in a country that has been attacked and the civilian population there is being bombarded on a regular basis by an aggressor country. The natural reaction is to stop funneling money to that aggressor country.

That's not "political".

You should be able to remember China invading other places historically. Recently, of course, China doesn't compare to Russia or the US in terms of direct conflict. On the other hand, they're the country that is the most vocal about an imminent occupation.

> should be able to remember China invading other places historically

Can you help me out by clarifying the time and the country they invaded? I remember China being constantly invaded by others, hence the building of the Great Wall of China. They also had a navy at some point exploring the world, but then stopped and never really colonized any place as far as I know. Of course, I don't remember the entire history of China by heart, so which place did they invade and when?

Deaths in Russia’s invasion of Ukraine: ~600,000 Total deaths in Israel-Palestine conflict since 1948: ~200,000. So Ukraine is definitely bloodier.

The area occupied by Russia in Ukraine is 20x the size of Gaza + the West Bank, and is 5 times the size of Israel itself.

Russia is 775x the size of Israel, so unlike Israel-Palestine fighting over a small piece of territory to live on, Russia’s war is far more pointless.

How many billions of dollars has the USA given to Russia since starting the war?

Truth is the first victim of any war.

"War is the continuation of politics by other means" - Carl von Clausewitz

But I do not see in the slightest how boycotting Kagi, or any other company who technically does business with some entity in Russia, helps the Ukrainians. Avoiding money to their businesses directly involved in the war efforts (arms, etc)? Sure, I get that. But yandex is only involved in the sense that the entire Russian economy is in some technical sense involved. I don't believe in punishing random Russians or Russian companies for the actions of their authoritarian, despotic government.

And to whatever extent it would have a miniscule impact, I believe that the impact it has on pushing tech companies more broadly towards user-first and user-aligned behavior far outweighs that. That isn't to say that that goal is more important than Ukrainians winning the war, it's not, or even very close, but the way we as westerners can actually make a difference is telling our politicians that we stand with Ukraine. A single phone call or letter to your representative would MASSIVELY outweigh a subscription to Kagi. }

So have you messaged your representative? If not, then I find this performative, and in either case, I am highly skeptical that it makes any practical difference.

As always, I'm open to having my mind changed.

> I am open to having my mind changed. Also I think you are arguing on bad faith.

My dude.

If a country goes into a neighboring country and starts killing people there, the natural reaction from a civilized planet would be to, at the very least, ostracize the aggressor. It should never pay to invade other countries. Invading other countries should be an obvious path to a total destruction of domestic economy and prospects for the future.

In other words, it doesn't matter if your money paid to Yandex goes directly towards bombs and drones (it actually does, if you look at the ownership structure). What matters Russian economy as a whole.

How are they going to enforce the 50 search limit? IP address?

I love the philosophy of just taking money from users and working on giving them what they want and having nobody else to answer to, and I think the results from that philosophy have been excellent. But my biggest (only) complaints are both difficult to solve for a paid search engine that requires login.

First, sometimes I end up logged out. And maybe I've changed my password in the meantime and it's not saved on the machine I'm logged out on. It is supremely frustrating to search for something and be met with a login screen instead, and enraging if I can't immediately solve it by logging in.

I'm hopeful that I can actually just search logged out now if this happens, and log in after I'm done with what I was doing.

The second is the requirement to install a browser extension in order to search from the unified search/url bar. I really wish browser vendors -- or, well, Apple is the only one I care about -- would support it directly.

I think they don't want to support a search engine that requires an account. It would be cool if the 100 free searches is progress in this direction but I'm not sure if it will be.

May I recommend a password manager, e.g. KeePassXC[0], with a YubiKey[1] and some folder synchronization across machines?

[0]: https://keepassxc.org/

[1]: https://keepassxc.org/docs/#faq-yubikey-howto

Case 1: Kagi extension for Safari redirects from Ecosia to Kagi when on the good path. I rely on this mostly because it’s first-party so there’s a bit more trust with my queries.

Case 2: Safari Redirect Extension [1] redirects unauthenticated Kagi pages to Golink. Golink redirects back to the original page with a Kagi Token appended. Instantly authenticated.

Also, I highly recommend setting custom DNS records on Ecosia/DDG/whoever-you-redirect-from to prevent query leakage.

[0] https://github.com/tailscale/golink

[1] https://apps.apple.com/us/app/redirectweb-smart-url-router/i...

I have a bookmark for `https://kagi.com/search?token=...&q=%s` (you can get the token from somewhere in the settings) and a keyword `k`. When I want to search, I type `k giant isopod` and hit enter -- that takes me to the search results. Note that that also works in private browsing windows, whether you want it to or not. :-P So you never have to worry about whether you're signed in.

Keyword searches are cool because you can use them for any site that exposes a query through any part of the URL.

That's definitely possible without installing an extension, you can add any search engine you want:

https://help.kagi.com/kagi/getting-started/setting-default/f...

(The instructions you linked are for Firefox)

If my agents are running internet search for me; why should I pay extra? My usage of Kagi has diminished since the raise of agents, so it should compensate. Maybe simply adding a soft cap to prevent abuse, but that's a bit lame to have to pay twice.

But those are an offer and are used to advertise and get more users. Not to mention, as the "50/100" says, they're capped.

I don't get it, what other sense is there? Seems like 50 daily API queries would be lighter weight than 50 browser queries. And with an API you can require a key (aka subscriber).

> But those are an offer and are used to advertise and get more users.

"Try our search engine from your browser" / "Try our search engine from your agent setup" These both seem like user acquisition pitches. The real difference with programmatic access is that you'll likely get users hitting the cap and paying for more usage if they like the product.

> as the "50/100" says, they're capped.

... which is exactly what I was suggesting for API use.

Obvioulsy the TYPE and RETURNS of some cost.

>These both seem like user acquisition pitches. The real difference with programmatic access is that you'll likely get users hitting the cap and paying for more usage if they like the product.

50 searches from the web feel way more generous to a user than using the agent (most wont even hit them), hitting the 50 cap in like 10 minutes, and being negative about the whole experience.

>... which is exactly what I was suggesting for API use.

Which is exactly why it wouldn't work well for API use with such cap.

When a real user is going through the trial period, those 50 searches get them familiar with the tool. When their usage runs out, they're forced to decide if they want to pay to continue or invest the work into replacing it.

AI agents typically don't care. They may sign up for a trial, use the trial, and then when the trial runs out they might get creative and create a new account, or silently switch to another service to avoid bothering the user.

Browsing some of the forums where people discuss their search setups is enlightening. The current favorite strategy is to have your AI set up access to all of the different search providers with free tiers and then rotate among them to avoid having to pay for anything.

Defeats the purpose of the free tier.

Interesting, is this for personal use or is it some business application? In any event I'd imagine the same can be done via agents using a browser.

> AI agents typically don't care. They may sign up for a trial, use the trial, and then when the trial runs out they might get creative and create a new account, or silently switch to another service to avoid bothering the user.

That is a crazy amount of compute just to conduct a search.

It's the people downloading open weight models and running OpenClaw (or this month's trend) who don't care how many tokens it takes because it only costs them electricity.

Real businesses aren't doing stuff like this.

It's the home users who use LLMs as a hobby. Some power users pay for Exa and other services. A lot of home LLM users will go to unbelievable lengths to not pay for anything that isn't hardware. Seeing what your agent can do is half the fun for them.

Set one of them against a goal and tell it to not bother you until it has the answer. They will do some weird things as they go.

I refuse to believe there is a negligible margin decrease for agents using the regular search budget. Searching is cheap.

That’s a bad business decision in the same way it would be a bad business decision for Netflix to re-enable infinite account sharing.

Right now, API usage is only available using a PAYG credit system, even if you've already got a subscription. But giving subscription users an allotment of free credits that covers light API usage would be nice - I could plug it into my agent of choice for casual chats or exploration, while still having to buy credits for more extreme or production usage.

e.g. if you expect the average user to use 50% of the search quota / month through the UI, but 100% through the API, then you make the quota shared between the two but double the effect of usage from the API.

Especially if the API induces demand.

(Don't shoot the messenger, just trying to explain why it makes sense that they're not doing this)

[1] Meaning, they are more satisfied with an 'unlimited' or just way-more-than-you'll-ever-need option, even when it costs them more when averaged over even a few months. I'm not saying this makes you an irrational person -- I have the same illogical feelings myself.

This is why unlimited or at least a service stop instead of overage is highly preferable. It's the reason I only use prepaid mobile plans too so they can never overcharge me (and it's cheaper than a contract too)

I'm imagining rate limits that would prevent the user from making many more API calls than they would have made searches anyway. If you want unlimited 24/7 searches, you can pay for the credits directly, but if you just want to partially replace your existing search habits with e.g. interactive agent sessions, then that would be fine.

A more specific example would be how Anthropic allow certain Claude subscriptions to get free API credits, with some restrictions on the age of the account and with the number of credits being limited.

I think there is a workable solution here, although I can imagine that figuring out the details (how many credits to offer, what sort of limits, how to price the whole thing, etc) is complicated enough that Kagi have decided it's not worth the effort for the small number of users for whom this feature would be useful. And generally I'm very satisfied with Kagi, so I'm not complaining here or trying to suggest that this is something that they should be expected to offer. It would just be nice!

A bit off-topic, but when I signed up for Kagi, I naturally became more aware of how many times I use search on the internet, since I didn't want to run into the limit for my tier.

I assumed I was a heavy search user, but now that I watch myself, I'm really surprised how little I actually search anymore. I thought it might be a hundred times a day. In reality, it's closer to four or five times a day.

I don't know if it's my changing habits; or the fact that much of the information on the internet has become siloed, so I know where to go without wandering around; or some other factor.

I was just really surprised.

I also see a lot less value from my Kagi subscription like the grandparent post than I did before agentic search. I’ve been wondering if I should just drop it in favor of DDG; allowing me to use some search via api would change that for me.

You're paying ten bucks a month for access to Kagi the web search, not Kagi the search API. If you want them to provide that service and scale it accordingly it makes sense for that to be a separate feature with a separate price.

The big difference is that API usage can be scaled up way quicker than web page hits and scraping can be, which is an understandable concern if you're trying to price your service for human usage and not for bots hammering away as fast as they can. But judicious use of rate limits could help here - have a subscribers API tier that allows only a relatively low volume of calls and do standard API pricing for all requests beyond that.

That said, I'm sure there are complexities here that I'm missing that make this easier to say than to do.

Is it plausible that Kagi's financials require them to run a tighter ship than established players?

Conversely, is it plausible that they are so popular that they can afford to be deaf to the negative UX of the extra sub?

I would suggest that the answers to those, and a quick survey of the heavy costs agentic use has imposed on site operator over the past few year5, suggest that this is a reasonable compromise that keeps costs down for the average user and moves agentic users to the API-fee paradigm that is already rather common.

Weaker on actual search features though

This said, it's a good offer. You can switch between many models quickly. They are rated by quality, speed and price, and it's shown with orange dollar symbols for price and bullets for speed and quality. Example:

    Anthropic Claude Opus 5.5

    Anthropic's flagship model with always-on adaptive
    thinking ($$$$$). Best for deep reasoning, agentic
    coding, and long-horizon work.

    Cost    $$$$$
    Quality ●●●●●
    Speed   ●●

The last time I used it heavily was a few months ago so it might have gotten better, and I assume the more expensive tier where you can choose which models it uses might be a bit better depending on which model you choose. I much prefer just pointing my own local agent harness at a search api at this point though.

I also don't need anything but search and image search: for maps I use OSM, for LLM inference there are various free and paid providers, for videos one sadly doesn't find much outside of youtube anyhow (save for specific genres like conference talks at media.ccc.de, in which case I already know where to go). All this stuff included in the ultra plus fancy version incurs costs for them so it makes sense that it's not in the base product, but I won't use it I feel silly paying for it

I use the 2-person plan with my wife which is unlimited for $14/2.

There is also a family plan which is unlimited for $20/6.

I don't see the problem. Even for a single person $7 is worth it but $10 is just too much? Eh, maybe. If they hadn't come out with the duo option I'm not sure what I would have done myself.

I actually agree about the AI. Pick almost any estimated value/cost you want for the AI and let me remove that and I would like to.

But $14/2 has been good enough to just ignore the AI and only be a little annoyed I'm helping pay for it.

https://kagi.com/pricing

The whole point of this comment chain is about not wanting to pay for access to something that they don't want. I've been subscribed to Kagi Ultimate for years now, but I totally get what they're saying. Having a "search only" subscription would be interesting, and probably boosted adoption a non-trivial amount.

I'm very cost conscious for services though. I wouldn't pay more than €3 a month or so. Being in a medium wage eu country I just don't want money flying or left right and center.

Google of course does not have a search API - Kagi is paying (IMO sketchy) SERP scrapers for these results. One of the reasons I canceled my subscription

They have since removed all mentions of it and other names of the indexes that they use from their docs.

Basically you have no transparency and no clue how much of your money is going where. Could be that 80% of your results are Google index, 10% Bing, 5% Yandex and 5% independent indexes and you have no way of knowing.

That's why I switched to Uruky, where I have actual control over where my money goes. I mainly use EUSP, Mojeek, Linkup, Marginalia and if I can't find what i'm looking for only then go to a fallback search engine (that you can set inside) like DDG, Brave, Ecosia. There's a couple of other smaller open source indexes that they use (including their own).

There were a few times where I would search for things and get some very, very weird results (e.g., when looking for GH repos, I'd find things at the top from places like gitmemory (I think that's what it was called)) and I thought that was very odd, but it hasn't really happened again in a few days so I don't know if it was just a bug or what.

I generally do less than 30 web-searches per month on not-topic-specific search engines (I have bookmarks for information sources on most topics I care about).

With this new no-account-needed free search option, I could probably get away with doing all my general web searching on Kagi, without ever being a paying customer. (Maybe requiring some occasional shenanigans such as clearing my cookies or changing my IP address or something)

But in the interest of being a "customer" (and/or a "supporter") rather than just a "user", I'd be willing/interested in buying a bucket of searches that don't expire. Or even with a long expiration date, like a year after purchase.

1. DDG

2. Google

3. Whichever LLM is closest at hand

4. This is information the world was not meant to know

(Also Marginalia for deep search)

I’m not sure if this holds true nowadays. I’d say it git pretty bad, but now Gemini summary pretty much covers all of my use cases. And for any meaningful query, it’s straight to ChatGPT/Claude.

My google queries are like different combos of weather, specific event questions, directly attributed to wikipedia data and etc. LLMs are way past the point of reliability when it comes to data extraction from static websites.

Two very modern counterexamples:

https://app.opencve.io/cve/CVE-2026-83844

https://www.sentinelone.com/vulnerability-database/cve-2026-...

The information they feed from is simple, clear, and static. And yet the both of them are hallucinating mitigations, compromise indicators, and other details of the vector that flatly don't exist.

The question GP posed wasn't bait. It's still a blatant problem in 2026. It's not just shitty cheap models, either. Just this morning I caught 6.1 Sol (via Codex) incorrectly answering a question about the codebase it was actively working in.

What a disgusting use of technology. Kicking a query to an agent, that's leveraging a model that has bulk of humanities information in it, so it can use a web browser to go looking for the thing you searched. WTF.

1. leverage the AI Overview model (with the IQ of a brain-damaged monkey),

2. run an ad auction and populate the first 6-10 items from that,

3. then do a perfunctory exercise of searching its spam-riddled index to round out a few results at the very bottom of the page.

Yeah, that guy asking ChatGPT is a monster.

Time and place for every tech/use case. When I’m in the mood for reading long pieces, i do that deliberately.

If you don't want to be banned, you're welcome to email [email protected] and give us reason to believe that you'll follow the rules in the future. They're here: https://news.ycombinator.com/newsguidelines.html.

If you don't want to be banned, you're welcome to email [email protected] and give us reason to believe that you'll follow the rules in the future. They're here: https://news.ycombinator.com/newsguidelines.html.

And I won't know which ones are the wrong ones, so I may as well trust it 0% of the time.

Most people I know use AI Overview now as their primary way of doing any sort of research or question-answering... and I urge them: If getting an LLM take is suitable for your purpose, at least ask free-tier ChatGPT, which is at least an order of magnitude less likely to vomit up false or confused information. Also, asking actual Gemini is another sane option that is far superior to AI Overview.

Most people are not asking google to build them a train signaling system but to look up some question on Wikipedia for which the answer does not matter that much

Think of the incentives and the path of absolute least resistance/thinking/energy use and you will arrive at the product people want.

Does truth matter in the post-truth world where disclaiming truthful news about you is as easy as calling it fake?

How do you live like this?

When I dismissed the popup, it produced much better results than screenshots I’ve seen from logged in browsers.

I guess that’s an improvement?

Come to think of it, one of my boxes is not logged into kagi, and is mostly ai nonsense.

I guess I’ll keep paying them. :-)

80% of the time the search results were perfectly fine, but that small amount of time would royally annoy me and my breaking point was this: https://i.redd.it/r4q6y3vl5vdh1.png

So I went back to Kagi and appreciate it a little more (they've also rolled back on Translate to some degree).

However, Google has shat the bed, itself, the room the bed is in, the neighbors and half of the city with the search. Since search no longer returns any semblance of relevant data, but ads and wrong AI summaries.

So for vast majority of use cases I find Kagi much more superior. And in 1 or 2 cases when I'm frustrated with the results I can append `g!` before the query to get the shitty Google results.

The only downside: Apple doesn't let you set a custom search engine to Kagi. And (a very unpleasant surprise for me) neither does Firefox. You need extensions.

(Does Chrome on mobile allow it? I use Edge on iOS which also only has a hardcoded list, so while I don't know for sure, but I assume not)

[1] no doubt i will be waiting until i am dead

Google intentionally serves bad results now to juice ad impressions (according to sworn testimony from their execs), so I assume DDG is significantly better these days.

- DDG

- Kagi

- Bing (10+ years ago)

- Yahoo (I'm getting old...)

I searched by typing lists of keywords into the search box in the past. Maybe you're one of those people that types sentences, or relies heavily on synonym matching? (Which finally works now, but only if you turn on LLM mode -- even then, Google shipped that months or years after kagi, and the reviews are scathing vs. the performance I get out of the Kagi AI search.)

[Citation Needed]

As for Google, I typically only use its "Web" search so I skip all the junk Google adds to the `All` tab. With Firefox or Chrome, you can make a custom search engine with `&udm=14` appended, like `https://www.google.com/search?q=%s&udm=14` if you want it to be your default search engine.

The last time kagi failed me, I flipped on claude research mode. It found a microfiche archive, OCR’ed it, then started retro-stalking obscure 90’s celebrities (read old interviews, found coworkers, etc).

It took 15 minutes, but it produced an accurate 20-30 page report, then converted it to machine readable form for downstream use. I tried doing the same research myself a few years ago and failed to find anything at all.

As the kids say: Google’s cooked.

I switched to Ecosia because I want to support European alternatives, but that's all. I tried Qwant for a while, and for some reason it was frustrating me (I assume that the results were not satisfying for me?). I wonder if Qwant is better for search in French? Not sure. Ecosia hasn't been frustrating though, and I cannot say that it's worse than my experience with Kagi. I just wish I could pay Ecosia instead of having ads (which my browser seems to block anyway).

Anyway, I always wonder why it is that a search engine (say Kagi, Ecosia) can "work well" and another one (in my case Qwant) can be "frustrating". If they all tap into Google/Bing and others anyway... I'd be curious if someone could explain!

But it seems Ecosia does really help around the world, at least looking at their reports certainly seems so. Even if it's not a huge impact, isn't it better than nothing? How does NOT using it help anyone?

Instead, just refusing a work trip or something once a year helps a lot more than using ecosia.

Still better than using Google directly.

I agree with you, it won't change the world. But again I think it's mainly just marketing. They do what they claim and they do seem to care about actually making a difference and are somewhat consistent with their efforts so I wouldn't call that "greenwashing". I don't think their efforts are minimal but what do I know about planting trees and stuff. You can check their youtube channel :

https://www.youtube.com/@Ecosia/videos

I genuinely don't care about their "green marketing". I use Ecosia because it is European, and it works for me as a search engine. As I said I tried Qwant but for some reason it was not working for me.

I do care a lot about ecology, but my choice of search engine is not really impacted by that. People who think that "planting trees" is helping the environment need to get informed about the problem.

Kagi uses a lot of different providers, including [Yandex](https://kagifeedback.org/d/5445-reconsider-yandex-integratio...).

I would recommend trying out [Uruky](https://uruky.com/) You can choose your own indexes to use. So if you want to support European companies you can try to use as much as possible European or open-source indexes and only when you can't find stuff to back to google's (they even have a private google index that they use called Serper). You can also configure fallback search engines like DDG, Brave...

And the UI is also cluttered with useless stuff I don't need.

I feel that we lost good search engines here.

This is more work up front, but I have a bot I communicate with via Telegram, and I've hooked up Kagi API Search and Extract, and now achieve something similar. I just ask it to do a web search to try to find the answer to my question.

It's pay-as-you-go. Not particularly expensive.

We'll need a way to hook up the agent to a subscriber search service.

Since work gives me a generous API token allowance only use the $20 sub for side projects but still going to hurt using Codex credits for regular ChatGPT questions. Has been my goto instead of Google also but.....

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

I suspect they are aware of their own leaderboards and use those in their ranking algorithm.

Is the 20th most visited website in the world.

[1] https://kagifeedback.org/d/3285-safe-search-dns-locking-for-...

Not working with Kagi, but while they have RU contracts this will not be possible, can guarantee.

Either way, ultimately the result of not offering the option will more likely be getting blocked entirely, than workers being freed from the shackles of SafeSearch.

Also blocking the search is pretty weird, what prevents me of typing the URL directly?

Not if the machine is locked down. Blocking all search engines is not a feasible approach, though, hence the Safe Search mechanism.

> Also blocking the search is pretty weird, what prevents me of typing the URL directly?

That URL can be blocked at the router level, but one can still see cached search engine images when safe search is off.

It's not just porn, it could be a way to prevent successful phishing through employees filling out a malicious form or whatever.

"Trust your workers" is bad infosec.

But blocking alternative search engines and AI engines goes a bit far IMO especially if they dont use training.

Their reason for demanding trust is that how dare you not trust them, which is how you can tell they're untrustworthy.

Some companies just know their workers, i.e. if you have a bigger company you will have some idiots. We heard things like "you shouldn't be paying an escort with your company credit card" and the reason was because it was done, multiple times.

Can you expand upon this? Why is there an AI block?

The reason is that copilot resells other people's models (they're just a middle man) and there's an easy way to cut them out. So they blow up the dangers of other people's AI. Whereas if your data is in M365 they have it all anyway whether you use copilot or not.

    [Cloudflare Turnstile] Error: 600010.
    600*  Generic challenge failure  Bot behavior detected.

If you wouldn't mind reviewing https://news.ycombinator.com/newsguidelines.html and taking the intended spirit of the site more to heart, we'd be grateful.

difficult to buy with no trial

Yandex also annoyed me by constantly wasting my time to have me prove i am human.

I assume this is Apple’s issue moreso than Kagi’s. If anyone is reading this from the Safari team, setting Kagi as default search is far too difficult and the app workaround is unreliable.

I continue to pay for Kagi despite barely using it (Kagi doesn’t charge you if you don’t search in a given month! Fantastically consumer friendly feature) but this issue makes it useless on my mobile devices where I use search most.

[0]: https://diataxis.fr/compass/

What I also don't understand is: so how does the counter work? If I register, I can search 100 times and then it's done? Do I move into the 5$ tier to continue and have "Enough searches to get you going", whatever that means? Because certainly it's not "Unlimited Kagi Search" since you have to pay 10$ for that.

The business model is what made me turn away right now. I don't like those kind of "funny things" around money I have to spend.

The “for everyone” is technically true, but practically meaningless. In the long term, the type of person who finds the subscription price too high to pay will still be unable to search with Kagi.

I understand that price also includes the AI stuff, but I’d rather use something like the ChatGPT app directly than go via Kagi for that.

Right now there’s $10 for unlimited search and AI stuff and $5 for limited search and AI stuff.

At what price point could Kagi offer unlimited search and no AI stuff?

Maybe if it was a secure instance you could order for your organisation. Like a police force or consulting company, where you don’t want people eavesdropping on your traffic.

Let me give you $1 or $2 per month (or $24/year) for my 10-ish search requests a week and you've got yourself a subscriber.

What is the value to society of having a search engine alternative that doesn't desperately mine and monetize every single thing about us they can?

It's not just a search engine subscription.

This could be a first step towards freeing us from advertising. An investment in an alternate vision that doesn't rely on rampant manipulation and consumerism.

The cost is, what, a few coffees per month? Can we afford to not support initiatives like this? We can steer away from a feudalist cyberpunk dystopia.

Yet, after all of that, I still don't want to pay $10/mo.