Live data from Hacker News

Kagi Bloopers – Search Results Gone Wrong

help.kagi.com

21–30 of 66 posts

Re: Kagi Bloopers – Search Results Gone Wrong

#21
post #9

Just going to drop a quick complaint here that none of these are search results . (though yes, they are funny)

People searched for something; these were the results. What else would you call it?

By that definition a 500 page would also be a search result. :-)

Re: Kagi Bloopers – Search Results Gone Wrong

#22

Is Kagi worth paying for? It's been on my radar for a while.

I think generally yes. I tried it out for free for a while, found it was substantially better than Google and DuckDuckGo, and paid for a subscription.

Recently it has not had such a strong quality margin, which I suspect is due to the AI slop that all of the search engines are fighting against (due to errors both ways in their detection). I'm hoping this is temporary.

To be clear, I don't use any of their features except search (and domain filtering).

Re: Kagi Bloopers – Search Results Gone Wrong

#23

Does Kagi have any value in the era of LLMs? My understanding is that it aggregates result from different providers.

If you don't understand the value of a search engine over an LLM, then you're not going to understand the relative value of different search engines.

Re: Kagi Bloopers – Search Results Gone Wrong

#24

Does Kagi have any value in the era of LLMs? My understanding is that it aggregates result from different providers.

Yes: you get reliable source information and don’t get inaccurate summaries. E.g. last week I used Gemini to answer a plant biology question and got two contradictory answers based on minor variations in the wording because it incorrectly relied on blog spam over peer-reviewed articles for the first query.

The initial false answer was baldly asserted by the LLM without sources in the first two paragraphs but some of the phrasing it used was enough to locate the non-authoritative blog content it was apparently laundering. Had it accurately cited sources, it would’ve been easy to see that this random WordPress site saying X wasn’t as authoritative as the PubMed hits saying !X.

Re: Kagi Bloopers – Search Results Gone Wrong

#27

Is Kagi worth paying for? It's been on my radar for a while.

Just be aware that a small percentage of your money would be going to the Russian government: https://ounapuu.ee/posts/2025/07/17/kagi/

also duckduckgo use(d) yandex. not many alternatives in this space

Re: Kagi Bloopers – Search Results Gone Wrong

#28
post #3

“Pure numbers and French are not compatible” Yep that checks out

Sixty-ten-eight! Sixty-ten-nine! Four-twenties! 1999 == One thousand, nine hundreds, four twenties, ten, nine. I studied French in grade school over ten years and I love it. But the way numbers convert into language is wild. I tease it with love.

"Four twenties and ten" is better than the Danish "five minus a half, times twenty".

Re: Kagi Bloopers – Search Results Gone Wrong

#29
post #3

“Pure numbers and French are not compatible” Yep that checks out

Sixty-ten-eight! Sixty-ten-nine! Four-twenties! 1999 == One thousand, nine hundreds, four twenties, ten, nine. I studied French in grade school over ten years and I love it. But the way numbers convert into language is wild. I tease it with love.

US time: a quarter till 8.

Re: Kagi Bloopers – Search Results Gone Wrong

#30

Is Kagi worth paying for? It's been on my radar for a while.

My wife and I got the duo package because we do a lot of writing and need citations and sources. Compared to google and DDG it is less noisy and returns fewer spammy pages. We’re giving it a year to see if it is worth it.
Post reply on HN