> Kagi is not only an ad-free subscription. It’s a mental budget booster.

Likely, the "It's not X, it's Y" phrasing is what probably rang the LLM alarm bells.

LLM's are trained on human phrasings. So now we can't use human phrasings anymore?

I am one of those people that used to write em dashes – and now I self-censor them out of my writings :(

I still use them too. Don’t listen to these nerds. Self censoring is awful.

Yeah, I figured the same thing after reading my comment and chuckled. :)

Wow! Can I ask how Kagi is best for your uses? Would love to try myself

Oh, this appeared late in my feed.

I personally like the ability to filter my own results by promoting, demoting or blocking certain domains to filter lower quality results further. Same for image search which can also filter out AI generated images.

Also, I find lenses very useful (which is a way to limit your search radius) to search for specific things in the specific parts of the internet. i.e. you can define a lens with specific websites for a subject, and if you need something precisely, you can only search these websites.

I recently started to use SlopStop reporting to weed out AI generated webpages from search results, too.

Lastly, all AI features are opt-in. No summaries, no widgets, no extra "bells and whistles" if you don't want on your result page.

> I personally like the ability to filter my own results by promoting, demoting or blocking certain domains to filter lower quality results further.

I had an annual Kagi subscription that I let lapse not long ago. That was hands-down the best feature, so I vibecoded a small userscript that replicates it for DuckDuckGo. DDG also lets you turn off ads.

I'd gladly return once they fix the integration issues. In Safari, the redirect via the extension is a bit wonky at times.