Live data from Hacker News

Kagi Bloopers – Search Results Gone Wrong

help.kagi.com

61–66 of 66 posts

Re: Kagi Bloopers – Search Results Gone Wrong

#61
post #13

Given the title "Search Results Gone Wrong", I'd like to take this opportunity to try to shame Kagi into fixing the search results for the "More results" feature. This simple feature is broken in that it often gives you repeats of the same initial results it gave. That is, instead of giving you "More results", it gives you a lot of "Same results". I reported this as a bug about 6 months ago, and was quickly told it w…

Huh. Yeah also in the FAQ they say that the reason why they return so few results is just because their ranking is so fantastic: https://help.kagi.com/kagi/faq/faq.html#why-does-kagi-return...

I feel like that is either hubris (they are overconfident in their ranking) or they have some other reason. Now you bring this up, and it seems to fit with the same kind of thing.

It reminds me of this article which brings up a bunch of suspicious things about search engines, and talks about how weird it is that so many engines limit how far you can go into the results: https://archive.org/details/search-timeline

Re: Kagi Bloopers – Search Results Gone Wrong

#62
post #12

Earlier quoted context omitted.

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.

Switzerland and Belgium got them right!

It’s a well-known phenomenon that with the internet and modern media, large countries’ version of a language can affect the speech of the smaller countries using that language. Think kids in Portugal today growing up using lots of Brazilian words to their parents’ dismay, or americanisms slipping into UK speech. This makes me wonder if any young Vallon French speakers have started to pick up standard French higher numerals.

Re: Kagi Bloopers – Search Results Gone Wrong

#63

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

The domain-block feature makes it worth it for me. Finally no longer having medium or userbenchmark pollute my search results.

This. Or quora or pinterest or twitter/x or etc etc

I can outright block domains or just adjust their weight. Great for my personal prefs but also huge with the family account and helping keep the BS out of sight for the kids without going full restrictive.

Re: Kagi Bloopers – Search Results Gone Wrong

#64
post #49

Earlier quoted context omitted.

You say that as if LLMs are a good thing.

You say that as if a technology can be easily classified as good or bad.

Touché.

Still, I think the down sides of LLMs outweigh the benefits for most use cases.

Re: Kagi Bloopers – Search Results Gone Wrong

#65

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

The domain-block feature makes it worth it for me. Finally no longer having medium or userbenchmark pollute my search results.

You can self host searxng and block domains - increase priority on some etc. I do it myself.

https://github.com/searxng/searxng

Re: Kagi Bloopers – Search Results Gone Wrong

#66

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

If you expect it to be as good as peak google results, no. If you need something that’s very noticeably better than its competition, then yes. If you are okay with all of the terrible that comes with using LLM services as a search engine replacement, then probably no. If you despise the amount of second guessing and source checking required to use LLMs as search tools, then yes.

It literally gives you google results (+ additional search providers, usually not in top results)... without the added spam. It's therefore superior to "peak google results".

What are you talking about LLM services? default search behavior does not use any LLMs (except any Google might use to reorder their top 10 results internally).

Post reply on HN