Hacker News new | ask | show | jobs
by smcleod 851 days ago
Early Kagi adopter here. I love Kagi search and their summarisation features, but I'd rather they just focus on high quality and configurable search and summarisation results rather than new products.
2 comments

I suspect their core business is unsustainable as is. From what I understand, they use search APIs, which are expensive. So they need to get their own index, at least partial, to have a sustainable business.
Kagi employee here. The search business is sustainable, we don't need a push in AI things to make it work. We're looking at these features/ideas because we think they complement search well, not because we need them from a cashflow perspective :)
Duck Duck Go uses the Bing API and they've been around for a long while. I'd imagine there's a heavy 80/20 rule of data that needs to be indexed frequently that people also search for, so those same cached results from API calls get the most use.

Just speculation though.

I don't think it's a fair comparison. Every single other search engine sells ads including ddg. Sure, they don't track you, but will still serve ads for your quesries.

Kagi is explicitly an ad free subscription. Comparing profitability is not straightforward.

Right, but the majority of Kagi users pay $10 a month. I doubt DDG is getting $10 per user per month in revenue.
DDG search results are dreadful compared to Kagi, not even slightly compatible.
It seems like a feature which is mutually beneficial. Ie user activity on embedded sites helps indicate interest in Kagi index updates.

Isn't this entirely in-line with your desires? Better quality search results by way of having up to date indexes?

The problem is that it can go also terribly wrong. (New way for SEO optimisation)
Kagi users are in such a minority that I don't see how it is worth it for anyone to optimize for Kagi search results.
Yet. If you want to be better than Google, you need to avoid Google's mistakes.
Tiny Kagi has already shown an ability to produce better results than massive Google, despite them both dealing with the same SEO site gaming/structuring. Which is the reverse of what would be expected if Google's greater resources were also focused on quality.

Kagi already dodges the SEO bullet.

Disclaimer: I pay for Kagi. You should too!

If the userbase grows enough (let's say 100x that of today), they could become an SEO target. As happy as I am with the current results I am aware that SEO gaming is only a problem once scale is relevant. Once there are teams of people reverse engineering kagi's ranking explicitly wanting to beat it.

There's a good chance not enough people are willing to pay for search and this never becomes a problem.

Disclaimer: happy paying customer.

Paying Kagi customer here as well.

Kagi is leagues better than now-Google. It is about on par, slightly worse than the Google of yore — not by their own fault, but because they operate in a much more professionalized, difficult, hostile web.

They didn't dodge the SEO bullet — nobody has aimed at them yet.

> the same SEO site gaming/structuring.

This isn’t totally true. They can dodge a lot of stuff, because optimisations target Google’s algorithms, not Kagis. And Google also has conflicting intrests on same cases to let them just be.

I have paid for long time as well. But this brings new ”attack vector”, which is important to consider.

With Kagi’s customers being users, not advertisers, they can put in features to mitigate against problems caused by SEO, like how Kagi bundles up all the “Top X abcdefg” lists that turned Google into trash.
The parent context was:

> Ie user activity on embedded sites helps indicate interest in Kagi index updates.

Doesn’t this mean anyone? And once someone fakes user activity, that make it useless measure in the end.

This seems like a problem of the search space rather than solely Google's. How are you supposed to guard a system which, by its nature, provides financial incentive to others to game it?

No matter what weights and checks are put in place, some observers will notice how their rankings change and make appropriate modifications.

This isn't solved by Kagi's product, either. I'm a happy user and use it as my daily driver. That doesn't mean that, if it increases in popularity, the results will remain unskewed.

That is true. But you can still try to learn from others mistakes to make it as hard as possible?
No one would want to target developers with their warez.