Basically the title.
I’m interested in any opportunity to inprove the way I navigate the internet. What I’ve been for a few years now is DDG, which works fine. Not great, not amazing, just fine. And that’s ok considering how they opperate.
I just heard about kagi and was really cosidering it. Makes sense as a business model (pay so we don’t have to sell you data), seems privacy respecting, and claims to strive for best search results in the market. Some test searches from the trial seem promising.
If you’ve used it for any amount of time, what has your experience been with it? What plan are you using? What are you mostly searching for?
Even you haven’t used it, any thoughts / opinions are welcome.
Interesting concept, curious if it does decent results. Wonder if it has any biases towards certain things. How is it indexing? Is it going to have searches full of link farms? I do see a trial of it that I guess one could test initially to see how it does. I do see they have a browser as well, but it’s Mac/iOS only.
I was chatting about it yesterday here in this thread
-
I use the 10/month plan with a $5.0 soft limit and a $10 hard limit, though I have yet to exceed my plan quota at all.
-
I have used it since hearing about it on HN a couple months ago during one of the DDG controversies.
-
Its completely replaced my search engine. I use it on my work machines, personal machines and phone for all searching.
-
Most searches are probably work related ie: Systems Admin, “Devops” (depending on your definition of the term), Security etc etc but also random thoughts. Heck today i was searching for flounder lights on it.
-
I generally find I have to refine searches less often, and rarely do I need to use bangs to pipe a search to DDG. I have had co-workers mention in recent months that they are always amazed that I will find very relevant sources fairly quickly, often ones that they cant get a front page hit on even when looking for it because i mentioned it. Though that may speak more to how I structure searches already since Kagi is fairly new to me.
-
I use the filters/lenses quite often. The recipes one is awesome for a lot of the cooking/smoking I do. Programming is solid too.
-
I would NOT reccomend this for general use yet unless it has a specific value add, such as with me and work. For example my wife still uses DDG (because i put her on it) and probably google on work devices or something. Its fine for her and thus for me. I would only reccomend it if you happen to work in a specific field that has a TON of crap sourcing/junk articles that are SEO gamed (ie: Tech) or you specifically align with the privacy ideology.
-
the account thing is only for stripe for billing for now, they go have a greyed out and unchecked box enable query history. I have seen it mentioned you can use a totally fake email to sign up (since it doesnt necessarily require verification) though the owner has recommended against it for obvious reasons. Adding crypto options brings baggage, I think he just tied it to stripe to the ease of billing/use.
I’m weirded out by their “why need an account” explanation when Mullvad has a perfectly viable solution that doesn’t require one. “We don’t link your queries to you” is a vastly different claim from a “we can’t link your queries to you” one. Still, considering who we compare them to…
On a personal note, Google search is so infuriatingly shitty lately that I’d been thinking about switching to another service. This does look to be worth a try.
Well Mullvad can only offer that because they require you to be on their VPN. How would Kagi enforce their payment plan without an account?
Mullvad can offer that because they generate you a one time access token that’s good until a certain time for a set number of simultaneous clients.
Kagi could do a simpler version - an access token that’s good until a certain number of searches. In fact, they have that mostly built - the link they tell you to use in private sessions is literally it.
Add to that anonymized payment options, and you got yourself a hard to track design.
Yeah +1 on Google Search becoming shit lately. I shifted to DDG for a while but settled on Brave Search for now. Their new AI summarizer is quite good and I like how they club Discussion posts together.
I’ve been a Kagi user since launch, and it has completely replaced everything for me except image searches. It’s the best $10 I spend each month.
I fully agree! Furthermore, I use their Universal Summarize to summarise any web page and FastGPT for GPT related stuff. Both accessible through search bangs 😊
Same experience here. I tried Kagi when I got a new job and I thought that having a good search engine would be beneficial to me. It is indeed the best search engine I’ve ever used and I won’t stop using it.
The issues because there are some: it’s a bit expensive (but I gain at least 1 hour every day as I am not struggling with shitty results from Google), and the “privacy” of your searches cannot be proved once and for all even if they swear they don’t store anything.
Haven’t used it, but according to their Privacy & Terms they started using FastGPT which is a dealbreaker for me. I’ll stick to SearX which allows more curation.
they started using FastGPT which is a dealbreaker for me.
Care to elaborate on why? I haven’t being keeping up with all the AIs, and a 3 second search isn’t returning anything nefarious.
Accuracy. They are known to hallucinate. Sifting through various sources to verify information is already time consuming task without AI created nonsense that is impossible to source check.
FWIW, the AI features are not used to provide search results; they are all on-demand and triggered by the user (via Quick Answer, or Universal Summarizer, or the “discuss this site” feature).
The founder is well aware of the problems with AI and that is taken into account when deciding how to use it in Kagi.
See this link: https://blog.kagi.com/kagi-ai-search#philosophy
Generative AI is a hot topic, but the technology still has flaws. Critics of AI warn that “[AI] will degrade our science and debase our ethics by incorporating into our technology a fundamentally flawed conception of language and knowledge”.
From an information retrieval point of view, relevant to our context of a search engine, we should acknowledge the two main limitations of the current generation of AI.
Large language models (LLMs) should not be blindly trusted to provide factual information accurately. They have a significant risk of generating incorrect information or fabricating details (confabulating). This can easily mislead people who are not approaching LLMs pragmatically. (This is a product of auto-regressive nature of these models where the output is predicted one token at a time, and once it strays away from the “correct” path, for which the probablity grows exponentially with the length of the output, it is “doomed” to the end of output, without the ability to plan ahead or correct itself).
LLMs are not intelligent in the human sense. They have no understanding of the actual physical world. They do not have their own genuine opinions, emotions, or sense of self. We must avoid attributing human-like qualities to these systems or thinking of them as having human-level abilities. They are limited AI technologies. (In a way, they are similar to how a wheel can get us from point A to point B, sometimes much more efficiently than human body can, but it lacks the ability to plan and the agility of human body to get us everywhere a human body can)
These limitations required us to pause and reflect on the impact on search experience, before incoporating this new technology for our customers. As a result, we came up with an AI integration philosophy that is guided by these principles:
AI should be used in closed, defined context relevant to search (don’t make a therapist inside the search engine, for example) AI should be used to enhance the search experience, not to create it or replace it (similar to how we use JavaScript in Kagi, where search still works perfectly fine when JS is disabled in the browser) AI should be used to the extent that it enhances our humanity, not diminish it (AI should be used to support users, not replace them)