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

Show HN: Boring Report, a news app that uses AI to desensationalize the news

boringreport.org

Post reply on HN
Print view View original

141–150 of 348 posts

Re: Show HN: Boring Report, a news app that uses AI to desensationalize the news

#141

Post by tethys »

Can’t say I‘m a regular user of Artifact, but I‘ve played around for a bit with their AI summarize feature and found it really satisfying. Very reliably tells you what‘s hiding behind clickbaity headlines and best of all, it works without having to confirm/close cookie dialogs or any other popovers first.

Edit: To give an example: Coming across the headline "Popular action series is cancelled after just one season", the summary really provides everything I want to know (or at least: to let me decide if I want to spend time actually reading the article):

> Cancelled after one season: CBS has axed action series True Lies, based on the 1994 film, after struggling to find its own identity.

> Mixed reviews and lack of audience: The show failed to gain a large enough audience despite starring actors like Steve Howey and Beverly D'Angelo.

Re: Show HN: Boring Report, a news app that uses AI to desensationalize the news

#142

Post by haldujai »

andrewxdiamond wrote: post #136
rs999gti wrote: post #133

There's already - https://www.allsides.com/unbiased-balanced-news It's shows left, center, and right bias of new articles. Read the 'From the center' version of articles, and the bias and sensationalism has been removed - https://www.allsides.com/story/media-industry-cnn-staffers-c...

Isn’t coming to a news story from these specific political viewpoints already a whole lot of bias? I don’t think we can boil down most things into three separate POV. Not everything needs to be looked at through a political party’s perspective

They actually use a 5-dimension political spectrum. Left-right is not specific to any political party, dates back 200+ years and is extensively used in academic and nonacademic literature.

What other system would you recommend for evaluating political bias in news?

Re: Show HN: Boring Report, a news app that uses AI to desensationalize the news

#144

Post by haldujai »

vippy wrote: post #139
andrewxdiamond wrote: post #136

Earlier quoted context omitted.

Isn’t coming to a news story from these specific political viewpoints already a whole lot of bias? I don’t think we can boil down most things into three separate POV. Not everything needs to be looked at through a political party’s perspective

Came to say this. The point seems not to be give an "all sides showing" but specifically to remove language that's designed to trigger our subcortical response systems.

Is that even possible? Take the specific language apart the choice of which stories to report on is already/can be highly biased.

Not sure a sanitized Fox News or NYT is “bias free” and is probably more dangerous than approaching the original articles knowing what their bias is.

With that said the product being demo-ed here is about sensationalism not bias per se as in this discussion.

Re: Show HN: Boring Report, a news app that uses AI to desensationalize the news

#145

Post by gnicholas »

Do you generate the headline from the original headline, or do you desensationalize the body of the article and then ask OpenAI to generate a headline based off of the new article body?

It seems like the latter might be better, since it ensures the headline actually matches the article below, as opposed to relying on a likely-clickbaity title that would no longer match the desensationalized article body.

Probably worth testing both ways to see what the results look like!

Re: Show HN: Boring Report, a news app that uses AI to desensationalize the news

#146

Post by ShadowBanThis01 »

pixl97 wrote: post #132
ShadowBanThis01 wrote: post #126

This should be useful for the ever-more-hyperbolic weather reports that dominate network news now. NBC News, almost every week: "20 million Americans threatened by severe weather this weekend!" "Bomb cyclone threatens 10 million people" "Atmospheric river menacing 18 million people" Translation: A rainy front is moving through several states.

I mean there is a different between 'getting some rain this weekend' and 'life threatening flooding'. The atmospheric river post would be an example of the second headline and should still maintain the necessary urgency and implied danger.

There is indeed a difference, but you wouldn't know it from listening to these breathless announcements every night.

What I hate about these particular (nearly verbatim) examples is the summing of the entire population of every state that might be touched by a system and barfing it out as if it's a body count.

And why all of a sudden does every weather phenomenon (or variant thereof) have a new sensational name?

And on a California-centric tangent: I also detest meaningless labels, which CA loves. For example, there's a RED FLAG WARNING! WTF is that supposed to mean? Are millions of people threatened by red flags? OH NOES!

And finally there's "sigalert." Insert giant eye-roll emoji.

Re: Show HN: Boring Report, a news app that uses AI to desensationalize the news

#148

Post by erehweb »

robertlagrant wrote: post #122

I'd love to see an ongoing set of graphs and data visualisations that show me what's going on. E.g. - how much are we borrowing this year and the last 50 years - what is net migration for the last 50 years - what is inflation for the last 50 years - what are the crime rates for the last 50 years - what are the violent crime rates for the last 50 years Don't know why I picked 50 every time, but I'd just love some key,…

Agree that this would be interesting, but your proposed solution would not address people not agreeing on facts, I think. People often (many on this site) say that they don't believe government inflation figures, or that underreporting of crime makes crime rates meaningless.

Re: Show HN: Boring Report, a news app that uses AI to desensationalize the news

#149

Post by TeMPOraL »

madeofpalk wrote: post #29
morsch wrote: post #22

JPMorgan Chase CEO Jamie Dimon testified before a Senate Banking, Housing, and Urban Affairs hearing on September 22, 2022. Dimon mentioned that as the U.S. nears a potential default on its sovereign debt, markets could experience panic. ... [1] He said that today, but in an interview with Bloomberg. The source article[2] just illustrates it with an archive photo from 2022, when he testified in a Senate hearing. Simi…

I've come around to there being legitimate usecases for this type of generative AI, but I don't think producing anything that's supposed to be "True" or "Correct" is one. I think the only useful usecases is for when you want to generate fiction.

Writing summaries of documents and correspondence is one of the major use cases of those models. Desensitionalization and debullshittification are very similar to summarization, so it stands to reason LLMs should handle these tasks just as well.

Re: Show HN: Boring Report, a news app that uses AI to desensationalize the news

#150

Post by perrygeo »

You've thrown out many subjective terms here: "catchy", "relevant", "sensationalist", "essential". How do you intend to define these and hold yourself accountable? How are you planning to keep your biases or the emergent biases of the underlying tech in check?

"just hand it to OpenAI and :shrug:" is not a responsible answer.

Post reply on HN