News for hackers. Stuff that matters.
Re:Kagi News by atonse on Tuesday September 30, 2025 @12:26PM (#45427564)
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 publishing once a day feel like great features.

Re:Kagi News by __jonas on Tuesday September 30, 2025 @12:37PM (#45427720)
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 three sections (Historical background, Technical details and Scientific significance) that don't cite any sources: https://kite.kagi.com/s/5e6qq2

Re:Kagi News by cogman10 on Tuesday September 30, 2025 @12:42PM (#45427796)
Oof, that one is particularly bad because it cites 3 sources which are all the same article.

Google points to phys and phys is a republish of the MIT article.

Re:Kagi News by rdlw on Tuesday September 30, 2025 @02:26PM (#45429243)
There's even a 'perspectives' section that tries to contrast two of the sources, but they're the same article.
Re:Kagi News by cogman10 on Tuesday September 30, 2025 @02:36PM (#45429366)
I can envision the day where an LLM article generator starts consuming LLM generated articles which were sourced from single articles (co-written by an LLM).
Re:Kagi News by atonse on Tuesday September 30, 2025 @12:59PM (#45428059)
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 by __jonas on Tuesday September 30, 2025 @01:14PM (#45428242)
> 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?).

The main point of my original comment was that I wanted to understand what this is, how it works and whether I can trust the information on there, because it wasn't completely clear to me.

I'm not super up to date with AI stuff, but my working knowledge is that I should never trust the output of an LLM and always verify it myself, so therefore I was wondering if this is just LLM output or if there is some human review process, or a mechanism related to the citation functions that makes it output of a different, more trusted category.

I did catch the message on the loading screen as well now, I do still think it could be a little more clear on the individual articles about it being LLM generated text, apart from that I think I understand somewhat better what it is now.

Re:Kagi News by jtbayly on Tuesday September 30, 2025 @02:05PM (#45428953)
> 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.

Either you mean every time you read something interesting (“huh”) you should check it. But in that case, why bother with reading the AI summary in the first place…

Or you mean that any time you read something that sounds wrong, you should check it. But in that case, everything false in the summaries that happens to sound true to you will be confirmed in your mind without you ever checking it.

Re:Kagi News by rdlw on Tuesday September 30, 2025 @02:31PM (#45429296)
> as opposed to what? human editors?

...yes? If I go to a website called "_ News" (present company included), I expect to see either news stories aggregated by humans or news stories written and fact checked by humans. That's why newspapers have fact checking departments, but they're being replaced by something with almost none of the utility and its proponents are framing the benefits of the old system as impossible or impractical.

Re:Kagi News by atonse on Tuesday September 30, 2025 @02:59PM (#45429678)
I think you misunderstood my comment. I wasn't challenging the concept of human editors and fact checkers. I was asking a parent for a clarification of what the parent post meant by outlining that they were LLM generated summaries.

Like, I was asking whether they were expecting the curation/summarization to be done by humans at Kagi News.

Re:Kagi News by hadlock on Tuesday September 30, 2025 @01:52PM (#45428762)
Publishing once a day to remove the "slot machine dopamine hit" is worth it for that alone. I have forever been looking for a peer/replacement to Google News, I was about to pony up for a Ground News subscription but I'll probably hold off for a couple more months. Alternatives to google news have been sorely lacking for over a decade, especially since google news got their mobile-first redesign which significantly and permanently weakened the product to meet some product manager's bonus-linked KPI. One more product to wean off the google mothership. Gmail is gonna be real hard though.
Re:Kagi News by jacobgkau on Tuesday September 30, 2025 @02:16PM (#45429114)
> Gmail is gonna be real hard though.

Gmail seems like the easiest piece of the Google puzzle to replace. Different calendar systems have different quirks around repeating events, you sometimes need to try a variety of search engines to find what you're looking for, Docs aren't bug-for-bug equivalent to the Office or iCloud competitors, YouTube has audience, monetization, and hosting scale... Gmail is just "make an email account with a different provider and switch all of your accounts to use the new address." They don't even give you that much storage for free Gmail; it's 15GB, which lots of other email providers can match (especially paid ones). You can import your old emails to your new provider or just store them offline with a variety of email clients.

Is updating all of your accounts (and telling your contacts about the new address) what you consider to be the hard part, or do you actually use any Gmail-specific features? Genuinely curious, as I tend to disregard almost all mail-provider-specific features that any of my mail providers try to get me excited about (Gmail occasionally adds some new trick, but Zoho Mail is especially bad about making me roll my eyes with their new feature notifications).

Re:Kagi News by wintermutestwin on Tuesday September 30, 2025 @03:01PM (#45429692)
I am sticking with this reprehensible company for email because their spam detection is awesome and I have found no clear measurements of detection to reasonably compare. I’d love to be proven wrong!
Re:Kagi News by gnud on Tuesday September 30, 2025 @05:09PM (#45431286)
Switched from Gmail to Fastmail about 10 years ago.

2-3 spam emails slip through every week, and sometimes a false positive happens when I sign up for something new. I don't see this as a huge problem, and I doubt Gmail is significantly better.

Re:Kagi News by flexagoon on Tuesday September 30, 2025 @10:23PM (#45433663)
Gmail significantly improved the email spam situation for everyone by aggressively pushing email security standards like DMARC/DKIM/SPF [1]. This came at the cost of basically no longer being able to selfhost your own email server though.

I agree with the other commenter, I use Fastmail and I get very few spam emails, most of which wouldn't have been detected by gmail either because they're basically legitimate looking emails advertising scams. I have a Gmail account I don't use and it seems like it receives about the same amount of spam, if not more.

1: https://www.cloudflare.com/en-gb/learning/email-security/dma...

Re:Kagi News by kid64 on Tuesday September 30, 2025 @11:56PM (#45434112)
I don't understand how this once-per-day thing, very obviously a cost-cutting measure, can be taken seriously as a "feature". Stories evolve throughout the day. If this is truly important to you, just screen shot Google News, then look at the screen shot all day.