The only “other engine” that matters is really a thin paid SERP façade in front of a scraped Google result. In other words, Kagi pays for access to an API whose implementation is basically live scraping Google and throwing away the ads.
There are a few other indexes that Kagi’s aggregator mixes in (such as Bing Search) but those haven’t been contributing much in terms of meaningful results. The sheer size of Google’s index still dwarfs all the others, including Bing Search.
So yes, Kagi doesn’t scrape but they pay SERP providers who do.
Marginalia likely returns better results than Google, when it returns useful results. DDG/Bing likely returns average quality results which can be better than Google's slop results. It's not true that Google is the only useful one.
They pay scraping sites for results, including SERP API. When I pointed this out, last time Kagi was discussed on Hacker News, an employee of Kagi said that they're trying to build their own internal index, but he didn't provide details.
> Reasoning models sometimes put everything in the reasoning field and hand back content: null, finish_reason: "stop". 345 completion tokens, HTTP 200, nothing to show the user.
This isn't necessarily an OpenRouter issue, Google's Gemini will sometimes do it on their own API. Since they summarize reasoning this means you pay the whole cost and can't get anything out of it.
> you can just clone the repo and make your own very easily
This is not the case for Nitter. It requires real X accounts to run, quite possibly hundreds or thousands for a major public instance. Creating X accounts currently requires phone number verification.
It is possible to create X accounts without a phone number. I run [service].miningtcup.me and it uses 5 accounts, none of which required phone numbers for me to create, and none of which I paid for. You just have to get creative.
Most of the time I see AI pastes it's "I saw someone describe 20% of a problem they're having so I pasted it into Claude and now I'm pasting Claude's vague overview of how maybe to fix it", which is absolutely worthless.
I looked at your comments and there's a bunch saying that Anubis is bad CS but none I could find saying what, exactly, you want Anubis to do instead. You sure are posting a lot about how it's bad, though.
It is interesting, this particular user seems extremely active in this thread. I'm not sure if they have a bone to pick with Anubis in particular or some other reason for disliking the software so much, but to me it does seem overzealous. Regardless of if it's "bad computer science" or what, Anubis works quite well and is easy to customise to target it to specific botnets, as I've done. And this is coming from someone trying to develop her own non-PoW anti-scraper system.
Basically all of them are botnets, yes. They generally claim to have consent but I'm pretty sure 99% of it is "some app the user uses has it buried in a 200 page ToS"-style consent.
>These SDKs, which are offered to developers across multiple mobile and desktop platforms, surreptitiously enroll user devices into the IPIDEA network.
If I install an app with a big ToS and buried in there is "we use third-party monetization SDKs" and buried in there is "welcome to our botnet" they do not actually have my consent.
AI writing is not high-quality writing. And I don't think it's trained on particularly high-quality writing, I'm pretty sure it's trained on SEO slop. The old outputs of gpt-4o that loved the word "delve" read just like SEO spam blogs.
> Why would you add a penalty of 50 ms at a minimum?
All of the customer service bots I've dealt with recently were reasoning models that thought for multiple seconds. I would not have noticed 50ms extra.
It's still the case that you pay less in the app. You get 'coins' for a daily check-in, which are automatically(?) applied as a discount. Most items either don't actually use them or only give you a pointless 1% off or something, but I've gotten a $12 microcontroller for $5, for example. I think some coupons are app-only, too (though most aliexpress sales are fake and are better thought of as the normal price).
Companies are not going to hire a mobile dev team to create an app to give you a way to pay them less for a good.
They hire a mobile dev team to create an app to give you a way to hand over data that you otherwise wouldn't, is technically impossible to do through a web browser, and is worth more than the discount that they give you for using the app.
>Our search results also include anonymized API calls to all major search result providers worldwide
reply