Kagi News • Hacker News Board

Re: Kagi News

#91

Post by flyer23 » Tue, Sep 30, 2025, 4:47 PM UTC

bobbylarrybobby wrote: post #75

buster wrote: post #5

Kagi seems to be one of the few companies that put out services, genuinely trying to fix things with good intent. I hope it stays that way. (I was very skeptical about Kagi Assistant but now i am a happy Kagi Ultimate subscriber).

I'm curious, aside from pricing, what utility do you get from Assistant that you wouldn't from just subscribing directly to a single LLM?

KI multi-step asisstant. Being able to try out all the llms in one subscription. Search integration with Kagi which means AI can really search only pages I want. And my settings for search as well.

Re: Kagi News

#92

Post by skybrian » Tue, Sep 30, 2025, 4:48 PM UTC

Do the checkmarks do anything? I expected them to disappear after a reload (like hiding a post on Hacker News), but apparently that's not what they're for.

"Mark as read" checks all the checkmarks, but since they're still there after a reload, I don't see the point.

Re: Kagi News

#93

Post by raincole » Tue, Sep 30, 2025, 4:48 PM UTC

__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

Re: Kagi News

#94

Post by kiicia » Tue, Sep 30, 2025, 4:48 PM UTC

__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 also publishes normal unabridged rss feed that you can read with rss reader of your choice, it looks like great news source

Re: Kagi News

#95

Post by eterm » Tue, Sep 30, 2025, 4:49 PM UTC

drewbitt wrote: post #80

I’m probably online too much, but a lot of the news I see is from yesterday. Supposedly it just refreshed with today’s news, but does that really clear out anything older if some outlets publish their stories later than others? I would not describe some of this as "today's headlines"

You might be online too much if you don't consider something that happened yesterday to be news.

An attitude of "Hook me up to the novelty juice, this is old weak sauce", is a sign of internet / news addiction.

Re: Kagi News

#96

Post by input_sh » Tue, Sep 30, 2025, 4:49 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…

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...

Re: Kagi News

#97

Post by ramesh31 » Tue, Sep 30, 2025, 4:53 PM UTC

>News is broken. We all know it, but we’ve somehow accepted it as inevitable.

News is broken because journalism is no longer a viable career path. No amount of RSS aggregators will fix that.

Re: Kagi News

#98

Post by drewbitt » Tue, Sep 30, 2025, 4:54 PM UTC

eterm wrote: post #95

drewbitt wrote: post #80

I’m probably online too much, but a lot of the news I see is from yesterday. Supposedly it just refreshed with today’s news, but does that really clear out anything older if some outlets publish their stories later than others? I would not describe some of this as "today's headlines"

You might be online too much if you don't consider something that happened yesterday to be news. An attitude of "Hook me up to the novelty juice, this is old weak sauce", is a sign of internet / news addiction.

I don't need the latest news. I would just like to know if something published happened yesterday or today at a glance.

Re: Kagi News

#99

Post by hereme888 » Tue, Sep 30, 2025, 4:55 PM UTC

clcaev wrote: post #34

What is the business model / exit strategy for Kagi's founders and investors? What is the news curation process and its relation to the public interest? Are these articulated in a manner which gives stakeholders (investors, users, and staff) assurances and standing? ... What are competitors and collaborators in this space? Semafor seems to have a similar product, what are the differentiators and/or collaboration oppo…

Read the "About" section of the page.

Re: Kagi News

#100

Post by lyu07282 » Tue, Sep 30, 2025, 4:56 PM UTC

boxed wrote: post #57

I think a fundamental issue with news is that it doesn't try to push people to have a more correct mental model of the world. Some things that could change that: - Deep fact checking. Community Notes on twitter do a better job at this than any other system I've seen. The reason it doesn't really work in practice is that the stream of misinformation and confusion is orders of magnitude larger than the Community Notes…

That's just media literacy I think. I would add to that "Sourcing": if the article just parrots some press release or badly summarizes some paper, it should at least link to that but they rarely do. Then it is hard to find the primary source, because you'll only find articles about it, not the actual primary source that they bury in google search.