Kagi News • Hacker News Board

Re: Kagi News

#101

Post by philipwhiuk » Tue, Sep 30, 2025, 4:58 PM UTC

BeetleB wrote: post #51

__jonas wrote: post #23

Just to be clear I'm understanding correctly: This is pulling the content of the RSS feeds of several news sites into the context window of an LLM and then asking it to summarize news items into articles and fill in the blanks? I'm asking because that is what it looks like, but AI / LLMs are not specifically mentioned in this blog post, they just say news are 'generated' under the 'News in your language' heading, whi…

It's not binary - it's a continuum. When you go to Google News, the way they group together stories is AI (pre-LLM technology). Kagi is merely taking it one step further. I agree with your concern. I see this as a convenient grouping, and if any interests me I can skip reading the LLM summary and just click on the sources they provide (making it similar to Google News).

> Kagi is merely taking it one step further.

I would argue creating your own summary is several steps beyond an ordering algorithm.

Re: Kagi News

#102

Post by meowface » Tue, Sep 30, 2025, 4:59 PM UTC

mvieira38 wrote: post #47

__jonas wrote: post #23

Just to be clear I'm understanding correctly: This is pulling the content of the RSS feeds of several news sites into the context window of an LLM and then asking it to summarize news items into articles and fill in the blanks? I'm asking because that is what it looks like, but AI / LLMs are not specifically mentioned in this blog post, they just say news are 'generated' under the 'News in your language' heading, whi…

Yes, that's what it is. Kagi as a brand is LLM-optimist, so you may be fundamentally at odds with them here... If it lessens the issue for you, the sources of each item are cited properly in every example I tried, so maybe you could treat it as a fancy link aggregator

I consider myself a major LLM optimist in many ways, but if I'm receiving a once per day curated news aggregation feed I feel I'd want a human eye. I guess an LLM in theory might have less of the biases found in humans, but you're trading one kind of bias for another.

Re: Kagi News

#103

Post by __jonas » Tue, Sep 30, 2025, 4:59 PM UTC

imiric wrote: post #61

__jonas wrote: post #23

Just to be clear I'm understanding correctly: This is pulling the content of the RSS feeds of several news sites into the context window of an LLM and then asking it to summarize news items into articles and fill in the blanks? I'm asking because that is what it looks like, but AI / LLMs are not specifically mentioned in this blog post, they just say news are 'generated' under the 'News in your language' heading, whi…

I'm firmly on the side of "AI" skepticism, but even I have to admit that this is a very good use of the tech. LLMs generally do a great job at summarizing text, which is essentially what this is. The sources could be statically defined in advance, given that they know where they pull the information from, so I don't think the LLM generates that content. So if this automates the process of fetching the top news from a…

I see! One thing I'm wondering: They say they are fetching the content from the RSS feeds of news outlets rather than scraping them, I haven't used RSS in a bit, but I recall most news outlets would usually not include the full article in their feed but just the headline or a small summary. I'd be worried that articles with misleading headlines (which are not uncommon) might cause this tool to generate incorrect news items, is that not a concern?

Re: Kagi News

#104

Post by leephillips » Tue, Sep 30, 2025, 4:59 PM UTC

mvieira38 wrote: post #47

__jonas wrote: post #23

Just to be clear I'm understanding correctly: This is pulling the content of the RSS feeds of several news sites into the context window of an LLM and then asking it to summarize news items into articles and fill in the blanks? I'm asking because that is what it looks like, but AI / LLMs are not specifically mentioned in this blog post, they just say news are 'generated' under the 'News in your language' heading, whi…

Yes, that's what it is. Kagi as a brand is LLM-optimist, so you may be fundamentally at odds with them here... If it lessens the issue for you, the sources of each item are cited properly in every example I tried, so maybe you could treat it as a fancy link aggregator

Hard pass then. I’m a happy Kagi search subscriber, but I certainly don’t want more AI slop in my life.

I use RSS with newsboat and I get mainstream news by visiting individual sites (nytimes.com, etc.) and using the Newshound aggregator. Also, of course, HN with https://hn-ai.org/

Re: Kagi News

#105

Post by atonse » Tue, Sep 30, 2025, 4:59 PM UTC

__jonas wrote: post #72

atonse wrote: post #56

Earlier quoted context omitted.

I'm genuinely asking, but have you tried it? https://kite.kagi.com It actually seems more like an aggregator (like ground.news) to me. And pretty much every single sentence cites the original article(s). There are nice summaries within an article. I think what they mean is that they generate a meta-article after combining the rest of them. There's nothing novel here. But the presentation of the meta-article and publi…

I have yeah, to me it looks like what I described in my comment above, it's LLM generated text, is it not? > And pretty much every single sentence cites the original article(s). Yeah but again, correct me if I'm wrong, but I don't think asking an LLM to provide a source / citation yields any guarantee that the text it generates alongside it is accurate. I also see a lot of text without any citations at all, here are…

They are LLM generated summaries, sure.

I guess I'm trying to understand your comment. Is there a distinction you're making between LLM summaries or LLM generated text, or are you stating that they aren't being transparent about the summaries being generated by LLMs (as opposed to what? human editors?).

Because at some point when I launched the app, it did say summaries might be inaccurate.

Looks like you found an example where it isn't properly citing the summaries. My guess is that they will tighten this up, because I looked mostly at the first and second page and most of those articles seemed to have citations in the summaries.

Like most people, I would want those everywhere to guard against potential hallucinations. No, the citations don't guarantee that there weren't any hallucinations, but if you read something that makes you go "huh" – the citations give you a low-friction opportunity to read more.

But another sibling commenter talked about the phys.org and google both pointing to the same thing. I agree, and this is exactly an issue I have with other aggregators like Ground.news.

They need to build some sort of graph that distills down duplicates. Like I don't need the article to say "30 sources" when 26 of them are just reprints of an AP/Reuters wire story. That shouldn't count as 30 sources.

Re: Kagi News

#106

Post by JohnFen » Tue, Sep 30, 2025, 5:01 PM UTC

raincole wrote: post #93

__jonas wrote: post #23

Just to be clear I'm understanding correctly: This is pulling the content of the RSS feeds of several news sites into the context window of an LLM and then asking it to summarize news items into articles and fill in the blanks? I'm asking because that is what it looks like, but AI / LLMs are not specifically mentioned in this blog post, they just say news are 'generated' under the 'News in your language' heading, whi…

Kagi is probably the only pro-LLM company praised on HN. Perhaps people's hatred towards Google outweighs that of LLM. Imagine if Google news use LLM to show summaries to the users without explicitly saying it's AI on the UI. Ironically, one of the first LLM-induced mistakes experienced by average people was a news summary: https://www.bbc.com/news/articles/cge93de21n0o.amp

> Kagi is probably the only pro-LLM company praised on HN.

Kagi made search useful again, and their genAI stuff can be easily ignored. Best of both worlds -- it remains useful for people like myself who don't want genAI involved, but there's genAI stuff for people who like that sort of thing.

That said, if their genAI stuff gets to be too hard to ignore, then I'd stop using or praising Kagi.

That this is about news also makes it less problematic for me. I just won't see it at all, since I don't go to Kagi for news in the first place.

Re: Kagi News

#107

Post by aleatorianator » Tue, Sep 30, 2025, 5:02 PM UTC

that "Kagi News" is at the top of "Hacker News" speaks volumes about the state of the "hacker"

Re: Kagi News

#108

Post by tolerance » Tue, Sep 30, 2025, 5:03 PM UTC

e40 wrote: post #42

I'm not affiliated, but I've used https://www.memeorandum.com/ for more than a decade. Gives me a good high-level view of the news. I'm a Kagi customer and I definitely don't want anything they do with the news.

This is it. This the one. How have I never heard of this and its related services? It looks perfect. Your own blog is interesting too.

Re: Kagi News

#109

Post by atonse » Tue, Sep 30, 2025, 5:03 PM UTC

input_sh wrote: post #96

imiric wrote: post #61

Earlier quoted context omitted.

I'm firmly on the side of "AI" skepticism, but even I have to admit that this is a very good use of the tech. LLMs generally do a great job at summarizing text, which is essentially what this is. The sources could be statically defined in advance, given that they know where they pull the information from, so I don't think the LLM generates that content. So if this automates the process of fetching the top news from a…

It's useful for the users, but tragically bad for anyone involved with journalism. Not that they're not used to getting fucked by search engines at this point, be it via AMP, instant answers, or AI overviews. Not that the userbase of 50k is big enough to matter right now, but still...

All this is doing is aggregating RSS feeds and linking to the original articles.

So this might result in lower traffic for "anyone involved in journalism" – but the constant doomscrolling is worse for society. So I think we can all agree that the industry needs to veer towards less quantity and more quality.

Re: Kagi News

#110

Post by krainboltgreene » Tue, Sep 30, 2025, 5:03 PM UTC

BeetleB wrote: post #51

__jonas wrote: post #23

Just to be clear I'm understanding correctly: This is pulling the content of the RSS feeds of several news sites into the context window of an LLM and then asking it to summarize news items into articles and fill in the blanks? I'm asking because that is what it looks like, but AI / LLMs are not specifically mentioned in this blog post, they just say news are 'generated' under the 'News in your language' heading, whi…

It's not binary - it's a continuum. When you go to Google News, the way they group together stories is AI (pre-LLM technology). Kagi is merely taking it one step further. I agree with your concern. I see this as a convenient grouping, and if any interests me I can skip reading the LLM summary and just click on the sources they provide (making it similar to Google News).

It cannot be "one step further", because there's a clear break in reality between what Google News provides and Kagi provides. Google News links to an article that exists in our world, 100%, no chance involved. Kagi uses an LLM generate text and thus is entirely up to chance.