Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Kagi News

blog.kagi.com

Post reply on HN
Print view View original

81–90 of 454 posts

Re: Kagi News

#81

Post by buster »

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?

Actually, i get the news search with a quick answer and a link to the assistent and not a single LLM but practically all LLMs in one interface and can link and share the chats. The Interface is nice, simple and Kagi is very up to date regarding new LLMs (it already contains Sonnet 4.5, for example).

It's just a nice interface for all LLMs which i often use on mobile or laptop for various work and also private tasks.

The last months have shown that there is no single LLM worth investing in (todays "top" LLM is tomorrows second-in-class).

Re: Kagi News

#82

Post by MostlyStable »

baggachipz wrote: post #33
daveoc64 wrote: post #19

The World section seems to have a heavy bias towards news from the USA. The UK section seems to have a heavy bias towards news from Scotland. It looks too simplistic for me to actually use.

Several sections have Trump in the headline. I wish there was a way to block that word like I do in Lemmy. That guy monopolizes the headlines which only makes him more powerful, and annoys me. I'll see whether I can take this when I use this new app, which I otherwise think is great.

This comment[0] suggests that they have some kind of a filter

[0] https://news.ycombinator.com/item?id=45427513

Re: Kagi News

#83

Post by threetonesun »

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…

We used to do this with a human created meta tag but I guess this is better?

Re: Kagi News

#84

Post by input_sh »

devmor wrote: post #37
__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…

The line “news stories will be generated” throws up red flags across the horizon for me. That’s not news. That’s news-adjacent random slop.

It's also a workaround around copyright, news sites would be (rightfully) pissed if you publicly post their articles in full and would argue that you're stealing their viewership. But, if you're essentially doing an automatic mash-up of five stories on the same topic from different sources, all of a sudden you're not doing anything wrong!

As an example from one of their sources, you can only re-publish a certain amount of words from an article in The Guardian (100 commercially, 500 non-comercially) without paying them.

Re: Kagi News

#85

Post by unshavedyak »

I like this a lot, going to try it! One issue i have though is in the current world of LLMs scraping content, i'd prefer there to be more discussion about compensation of authors.

I know the announcement page talks about not scraping, but to me personally the value i see in this product is that i don't have to go to those ad ridden, poorly organized and often terrible pages of the authors. Which then seems really unfair to the actual content providers.

I'd like to see this type of service cost $3-5/m ontop of my normal Kagi sub to compensate the authors of the articles i read. A Streaming Music model for news, ish.

This proposed value is quite small, but my assumption is only a very small amount of money would reach them from my ad views anyway so a $10/m addition feels extreme to me.

Re: Kagi News

#86

Post by cogman10 »

__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…

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

#87

Post by flyer23 »

I AM using it for a long time, its brilliant but as any ai can hallucinate. Joining 4 separate technical topics about 4 different companies and initiatives is funny but misleading. Wont go back though - HN+Kite is all I do.

Re: Kagi News

#88

Post by Spivak »

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?

The Kagi implementation can use Kagi search and can use advanced features of search like lenses. This isn't a unique feature but if you believe Kagi search is better than whoever Anthropic/OpenAI are using it's a nice plus.

Kagi's contracts with LLM providers are the ones businesses get with actual privacy protections which is also nice.

Re: Kagi News

#90

Post by lagrange77 »

Awesome, i like it a lot!

Some UX friction i noticed: To get back to the homepage from an article, i have to click on the article headline. While this is elegant and you likely get used to it, once you know it, it's not exactly intuitive.

Post reply on HN