I'm just happy to be able to entirely remove topics like sports. Google News no longer lets you do this, and gleefully pushes topics on me even when I religiously press "Show fewer stories like this"; it is infuriating. No I do not care about celebrities or football; stop insisting that I do!
Kagi News
151–160 of 454 posts
Re: Kagi News
#152Just 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…
> when you ask an LLM to point to 'sources' for the information it outputs, as far as I know there is no guarantee that those are correct A lot of times when I ask for a source, I get broken links. I'm not sure if the links existed at one point, or if the LLM is just hallucinating where it thinks a link should exist. CDN libraries, for example. Or sources to specific laws.
> A lot of times when I ask for a source,
They'll do pretty much everything you ask of them, so unless the text actually come from some source (via tool calls, injecting content into the context or other way), they'll make up a source rather than doing nothing, unless prompted otherwise.
Re: Kagi News
#153Given that this news is generated I have no idea why the default would be to be in the native language of the sources. And if that makes any sense I would need to be able to select multiple languages I want to read in because I can’t read all languages.
Re: Kagi News
#154Earlier quoted context omitted.
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/
> Also, of course, HN with https://hn-ai.org/
Ironically, this submission is at the top of that website :)
Re: Kagi News
#155Earlier quoted context omitted.
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'm about as AI-pessimist as it gets, but Kagi's use of LLMs is the most tasteful and practical I've seen. It's always completely opt-in (e.g. "append a ? to your search query if you want an AI summary", as opposed to Google's "append a swear word to your search query if you don't want one"), it's not pushy, and it's focused on summarizing and aggregating content rather than trying to make it up.
FYI, you can append &udm=14 to Google searches to remove AI results and a bunch of the other clutter they've added.
Re: Kagi News
#156Earlier 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...
What journalism? Most of these sites copy their content from each other or social media, and give it their own spin. Nowadays most of them use AI anyway.
Actual journalism doesn't rely on advertising, and is subscription based. Anyone interested in that is already subscribed to those sources, but that is not the audience this service is aiming for. Some people only want to spend a few minutes a day catching up with major events, and this service can do that for them. They're not the same people who would spend hours on news sites, so these sites are not missing any traffic.
Re: Kagi News
#157Something similar that collects news from various sources, plus it adds social media context: https://truenorthnews.app/
Re: Kagi News
#158Just 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 am fine with it using AI but it makes me feel pretty icky that they didn’t mention that this was ai/llm generated at any point in this article. That’s a no-no IMO, and has turned me off this pretty strongly.
Why do you care what technology was used to generate the summaries? What if they had used their old NLP summarizer?
Re: Kagi News
#159I think this is the wrong direction. We need better journalism, not better summarizing aggregators. Summaries are no substitute for real articles, even if they're generated by hand (and these apparently are not). Summaries are bound to strip the information of context, important details and analysis. There's also no accountability for the contents. Sure, there are links to the actual articles, but let's not kid ourse…
Also, they talk about "echo chambers" and "full spectrum of global perspectives". Representing all perspectives sounds great in theory, but how far should it go?
Should all politicians' remarks be reproduced verbatim with absolutely no commentary, no fact-checking and no context? Should an article about an airplane crossing the Pacific include "some experts believe that this is impossible because Earth is flat?"
Excessive bias in media is definitely a problem, but I don't think that completely unbiased media can exist while still being useful. In my expierence, people looking for it either haven't thought about it deeply enough, or they just want information that doesn't make their side look bad.
Re: Kagi News
#160Earlier quoted context omitted.
I'm about as AI-pessimist as it gets, but Kagi's use of LLMs is the most tasteful and practical I've seen. It's always completely opt-in (e.g. "append a ? to your search query if you want an AI summary", as opposed to Google's "append a swear word to your search query if you don't want one"), it's not pushy, and it's focused on summarizing and aggregating content rather than trying to make it up.
FYI, you can append &udm=14 to Google searches to remove AI results and a bunch of the other clutter they've added.
Neat trick, any other params folks might want to know about?