Live data from Hacker News

Kagi Small Web

kagi.com

211–220 of 223 posts

Re: Kagi Small Web

#211
This thread inspired me to build a decentralised tool to explore the small web: https://susam.net/wander/

If you like it and if you have a website, please join the network. It only takes uploading two files to your web server to set it up. In fact, you can host it on GitHub Pages or Codeberg Pages too. And you can link to any small website (not just blogs).

Details about how it works and how to set it up available here: https://codeberg.org/susam/wander#readme

Re: Kagi Small Web

#212
post #38

The first random page it returned to me was this — https://gaultier.github.io/blog/how_to_make_your_own_static_... — which was about building one's own static site generator, which I really liked. I did not realise when I closed that page how hard it would be to find it again, because, of course every new visit to Kagi returns a different page :-)

do you not have a browser history?

Re: Kagi Small Web

#213
Kagi betting on the small web is a smart differentiation play. Google has essentially optimized for large, authoritative domains — which means personal blogs, niche forums, and indie projects get buried even when they have the most relevant content for specific queries.

The small web is where genuine expertise lives. When I'm looking for a real opinion on a tool or a deep technical explanation, I almost never find it on the first page of Google anymore. It's all SEO-optimized content farm articles or AI-generated summaries. The actual expert wrote a blog post that's sitting on page 5.

The challenge is curation at scale. Manually identifying quality small web content works when the corpus is small, but maintaining quality as it grows requires either very good automated signals or a community-driven approach. Curious how Kagi balances this.

Re: Kagi Small Web

#214
post #186

Earlier quoted context omitted.

Sheldon Brown's content is great, but is it ironic that the first thing you see on his site is a Google banner ad? Understandably, he'd like to earn money on his content and I see no problem with that. But for me to visit his site and have Google add yet another tracking event to their "interest pile" about me (I guess i'm in the market for bikes now?) is a bit off putting. He can't be making more than a few bucks a…

As the author is dead, I'm sure the money goes towards site hosting fees.

I assume nobody removed it and the revenue is just added to some Google Adsense balance sheet, and reports go to some Gmail account that will expire one day.

Re: Kagi Small Web

#215

On a similar note, I maintain and grow a manually curated collection of personal blogs with valid RSS feeds: https://minifeed.net/blogs The criteria is simple: human-written (as much as I can validate myself), in English (for now), with valid RSS feed, and not a micro-blog (so, more than just feed of links or short tweet-like messages). Similar to Kagi's Small Web viewer, or StumbleUpon-style viewer: you can get a ra…

I was interested in something like this for while, thank you!

Re: Kagi Small Web

#216

Earlier quoted context omitted.

Tried it myself, first three I got were also about AI. Curious if there are any statistics on which topics people are writing about.

Click the Topics button.

How did I miss topics button!? It makes the whole experience absolutely different.

Re: Kagi Small Web

#217
post #163

Earlier quoted context omitted.

Only up to five of them, which is almost completely useless.

Blocking Pinterest is not completely useless.

The top seven blocked domains on Kagi are all Pinterest: https://kagi.com/stats?stat=insights

Failing to block Pinterest and then also having no room for anything else is almost completely useless.

Re: Kagi Small Web

#218

Earlier quoted context omitted.

It’s definitely not Kagi’s fault. The AI slop is simply taking effect and I feel sorry for them. I never expected them to match Google’s quality, but I was impressed with how close it was when I used it a few years ago.

Kagi used to use Google's search API. They discuss the current state of their index here: https://blog.kagi.com/waiting-dawn-search

Buried under a lot of complaints about fairness, Kagi mentions they are still using Google search results, just without authorization.

> Because direct licensing isn't available to us on compatible terms, we - like many others - use third-party API providers for SERP-style results (SERP meaning search engine results page).

So in one sense, yes, Kagi isn't quite Google, but in another sense, it very much still is.

Re: Kagi Small Web

#219
I don't know... It doesn't look very "small" to me. I "next post"ed a few, and most of them ended up being just some typical tech bro blog talking about boring tech.

But I did eventually stumble upon a post about two corgis, and another about medieval Europe...thingy. So it's not all bad.

Re: Kagi Small Web

#220
The insight that multi-agent coordination is fundamentally a type-checking problem — catch structural failures before spending the compute — is the most practical framing I've seen for this space. The adversarial composition example where information partitioning emerges from types rather than instructions is especially elegant. Looking forward to the follow-up on memory architecture.
Post reply on HN