411–420 of 454 posts
Earlier quoted context omitted.
The moon landing was filmed. Problem is, Stanley Kubrick was such a perfectionist that he _demanded_ they film on location.
On the other hand, he shot Full Metal Jacket in England and not Vietnam, so maybe he was able to compromise ..
Earlier quoted context omitted.
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.
> That's just media literacy I think The word "just" is doing a lot of heavy lifting there. Systems can change. Human brains on a population/genetic level can't. Blaming individual humans when we know statistically what they will do is mathematically equivalent to giving up. Also, giving someone information that turns out to be false and never following up isn't "media literacy". I can't see how it can possibly be.
> Systems can change. Human brains on a population/genetic level can't.
Realistically we can't fix media literacy education and we can't fix journalism, both are systemically broken. But I would never blame people, everyone is the product of their environment and a victim of the system.
> Also, giving someone information that turns out to be false and never following up isn't "media literacy". I can't see how it can possibly be.
Media literacy in that context would just refer to reliable sourcing, reliable sources post retractions/corrections.
Earlier quoted context omitted.
I like assistant, but I use Claude directly mostly. It's handy for really quick stuff though. I like that Kagi charges for their service, so their motive is to provide services for that cost, and not with ads on top of it.
It feels much less slimy to pay a nominal fee for a service than it does to use a "free" service and wonder about how / to what extent your data is being exploited.
- Allow me to have a single feed (as opposed to one tab/feed per category). Also, to prevent that feed from becoming too long, allow me to set a maximum number of news items or maximum number of minutes I'd like to spend. Prioritize/leave out news items accordingly. In other words: While I might be interested in sports, I'm not interested in reading or scrolling through as many news items about sports as about, say, world politics.
- "Highlights" and "perspectives" below the article text read like useless AI slop that merely reiterates the text, and artificially prolong an otherwise neatly concise page.
- Allow me to intersect categories and/or choose a regional "focus". Non-regional categories like "sports", "business", "technology" currently seem to aggregate news from across the world. However, I might be particularly¹ interested in a regional subset of e.g. business or sports news.
¹) I.e. not exclusively so. I'm still interested in world news but only when it comes to major events (in the sports case, say, world cups and championships).
Earlier quoted context omitted.
They don't explicitly say they generate summaries at any point in the article. In fact I read it and though this was just some fancy RSS aggregator. The way they describe the "daily briefing" is extremely ambiguous.
OK, but I'd like to repeat my question here: Why do you care how the summary was generated?
Earlier quoted context omitted.
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?" Exce…
> Should all politicians' remarks be reproduced verbatim with absolutely no commentary, no fact-checking and no context? Yes. That's an interview, and is much better than summarizations and short soundbites and one-sentence quotes.
> One daily update: We publish once per day around noon UTC, creating a natural endpoint to news consumption. This is a deliberate design choice that turns news from an endless habit into a contained ritual. I might not agree with all decisions Kagi makes, but this is gold. Endless scrolling is a big indicator that you're a consumer not a customer.
Now I just read the news on a Sunday (unless I'm doing something much more exciting). For the remainder of the week I don't read the news at all. It's the way my grandad used to read the news when he was a farmer.
I've found it to be a convenient format. It let's you stay informed, while it gives enough of a gap for news stories to develop and mature (unless they happen the day before). There's less speculation and rumours, and more established details, and it has reduced my day-to-day stress.
Annoyingly I still hear news from people around me, but I try to tune it out in the moment. I can't believe I used to consume news differently and it baffles me why I hear of people reading/watching/listening to the news 10+ times per day, including first thing when they awaken and last thing before they sleep. Our brains were not designed for this sort of thing.
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…
> 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.
The loop "create a research plan, load a few promising search results into context, summarize them with the original question in mind" is vastly superior to "freely associate tokens based on the user's question, and only think about sources once they dig deeper".
Earlier quoted context omitted.
> Should all politicians' remarks be reproduced verbatim with absolutely no commentary, no fact-checking and no context? Yes. That's an interview, and is much better than summarizations and short soundbites and one-sentence quotes.
Just printing whatever lies a politician or CEO says without any context or pushback is not a useful “news” source. You could just follow them on social media if you are into that sort of thing.
World leaders will always lie or side-step the truth in lesser or bigger degrees, because they represent a people or an organizations and committed fully to the interest of those. Part of being mature as a listener or reader is understanding that, and still get the useful information you need. Every person you meet in life will first and foremost speak from their own interest and agenda.
Then these interviews are complemented by regular reporting and interviews with people from the opposing viewpoint, if you so wish.