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

361–370 of 454 posts

Re: Kagi News

#361

Post by Nition »

AuthAuth wrote: post #353
bl4ckneon wrote: post #168

Earlier quoted context omitted.

How is Proton over extending? All of their services are pretty great imo. I'm happy with them. Doesn't mean I am ever going to use their bitcoin wallet app thing, but if they want to build it, great, they know their customer base so it's probably not out of left field.

In the drive mobile app you cant even download a folder. There has been issues opened on it for almost a year now and since then they've opened two entirely new services and added many extra features. When you're paying for something you expect the basics to be there and thats what annoys me about proton.

A similar one for Kagi: All other popular search engines have an alternative URL that enforces safesearch, allowing IT admins/parents to prevent safesearch being turned off at a DNS level (e.g. forcesafesearch.google.com, strict.bing.com). Kagi's had an open request for one for 3½ years[1] and it was recently downgraded in status away from Planned.

[1] https://kagifeedback.org/d/3285-safe-search-dns-locking-for-...

Re: Kagi News

#362

Post by totetsu »

pjc50 wrote: post #265
jazzyjackson wrote: post #228

Earlier quoted context omitted.

Love how it only took 8 years to go from "Fake News!" to "News May Be Fake"

There's too much demand for fake news, plenty of subsidy for it, and it's far easier to make. Non fake news is going to be restricted to pay services like Bloomberg terminals.

It seems a challenging situation.. if you pay fact checkers you get accused of censorship by “weaponised free speech” and if you leave it to the community you get inconsistent results.

Re: Kagi News

#363

Post by johnnyanmac »

totetsu wrote: post #362
pjc50 wrote: post #265

Earlier quoted context omitted.

There's too much demand for fake news, plenty of subsidy for it, and it's far easier to make. Non fake news is going to be restricted to pay services like Bloomberg terminals.

It seems a challenging situation.. if you pay fact checkers you get accused of censorship by “weaponised free speech” and if you leave it to the community you get inconsistent results.

The first one sounds like it's an argument made by someone who never wanted the facts to begin with. Correcting misinformation is not stifling free speech.

I'm all for more proper fact checkers, backed by reputable sources.

Re: Kagi News

#364

Post by devinprater »

After each headline on the page with all the tabs, there is an unlabeled button after each headline. Please, Kagi I beg of you, don't overextend yourselves.

Re: Kagi News

#365

Post by johnnyanmac »

bbor wrote: post #252
Harmon758 wrote: post #211

Earlier quoted context omitted.

Just for concrete confirmation that LLM(s) are being used, there's an open issue on the GitHub repository, on hallucinations with made up information, where a Kagi employee specifically mentions "an LLM hallucination problem": https://github.com/kagisearch/kite-public/issues/97 There's also a line at the bottom of the about page at https://kite.kagi.com/about that says "Summaries may contain errors. Please verify imp…

To take a moment to be a hopeless Stan for one of my all-time favorite companies: I don't think the summary above yours is fair, and I see why they don't center the summary part of it. Unlike the disastrous Apple feature from earlier this year (which is still available, somehow!), this isn't trying to transform individual articles. Rather, it's focused on capturing broader trends and giving just enough info to decide…

>giving just enough info to decide whether to click into any of the source articles.

If that info is hallucinated, then it's worse than useless. Click bait still attempts to represent the article, a hallucination isn't guaranteed to do thst.

Why not have someone properly vet out interesting and curious news and articles and provide traffic to their site? In this age of sincerity, proper citation is more vital than ever.

Re: Kagi News

#366

Post by flexagoon »

rwl wrote: post #205
meowface wrote: post #102

Earlier quoted context omitted.

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.

Indeed! A once per day human-curated news aggregation feed used to be called a "newspaper". You can still get them in some places, I believe.

This isn't really comparable. A newspaper is a single source. New York Times is a newspaper, CNN (a part of it) is a newspaper. Services like Kagi News, whether AI or human-curated, try to do aggregation and meta-analysis of many newspaper.

Re: Kagi News

#367

Post by flexagoon »

wintermutestwin wrote: post #240
jacobgkau wrote: post #201

Earlier quoted context omitted.

> 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 e…

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!

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

#369

Post by scosman »

coffeefirst wrote: post #330
__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…

Yeah. I really like Kagi. This is a terrible idea. 1. It seems to omit key facts from most stories. 2. No economic value is returned to the sources doing the original reporting. This is not okay. 3. If your summary device makes a mistake, and it will, you are absolutely on the hook for libel. There seem to be some misunderstandings about what news is and what’s makes it well-executed. It’s not the average, it’s the d…

Thank you. Also a paying Kagi user because I like the idea that it’s worth it to pay for a good service. Ripping off journalists/newspapers content goes against that.

Re: Kagi News

#370

Post by mkbelieve »

bl4ckneon wrote: post #168
tower-shield wrote: post #116

I like Kagi and want them to succeed. But currently (according to LinkedIn) theres 26 employees. They are building search, LLM assistant wrappers, a browser and now news. Please don't overextend the same way Proton is currently doing.

How is Proton over extending? All of their services are pretty great imo. I'm happy with them. Doesn't mean I am ever going to use their bitcoin wallet app thing, but if they want to build it, great, they know their customer base so it's probably not out of left field.

Buggy as hell. Proton Drive cost me a weekend and they lost me for life.
Post reply on HN