Live data from Hacker News

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

boringreport.org

261–270 of 348 posts

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

#261

Here's an idea, maybe the reason why news is angering and emotional is that there is a lot of bad shit going on in the world that we have just kind of let happen for a long time, and a lot of injustice that shouldn't be ignored, and a lot of people justice ignores that it shouldn't. Maybe the solution isn't to pretend things are just fine. People keep trying to paint this as some sort of "sensationalism" and "I want…

People getting angry at news is a major reason for a lot of the news that is worth getting angry at.

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

#262
I think that transformed news by language models is just another hole to jump in. I'm definitely tired of the internet being filled with mostly junk nowadays. I just don't like the idea of learning things via a language model. I prefer to filter this myself. Maybe it's more effort but to me feels more valuable. I mean we whine all the time about Google directing your searches to specific places. This feels the same of worse.

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

#263

The title from Boring Report: > The Legend of Zelda: Tears of the Kingdom Performance on Switch Article's title: > Zelda: Tears Of The Kingdom’s Performance On Switch Sounds Like A Minor Miracle I find the Boring Report summary to be much more informative that the article, it's like they trimmed away all the fat. The fact that the game runs at 20-30 FPS doesn't seem like a "minor miracle", by 2023 standards that's ba…

Ideally it would put the conclusions in the title:

> The Legend of Zelda: Tears of the Kingdom performance: 20 to 30 FPS on Nintendo Switch

That would generally make it unnecessary to read the article.

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

#264
post #13

I'm generally excited about something I'm calling "English to English translation" - and this is a good example. Previously translation has focused on going between languages. I think there's just as much benefit to translating within a given language. * Translate corporate speak to plain English. * Translate passive aggressive to calm and peaceful. * Translate sensationalist to neutral (like the OP). * Translate imp…

What you described is known as "sequence-to-sequence learning", or seq2seq. Google it or ask ChatGPT. It's a very common NLP technique that can do almost everything you mentioned.

Of course the utility will depend on the training data you collect. For example to go from corporate speak -> english you would need thousands of pairs of "translated" sentences. Or you could use an LLM to translate for you, paying as you go

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

#266
post #225
post #183

Earlier quoted context omitted.

Even then there's literally nothing stopping it from making shit up.

Sure yeah, for now. Just saying I literally use it to mine out things to confirm (/ not believe until I do) and so far it has very rarely led me astray and even then it's been small nuance. It's striking.

What do you mean "for now"? Yes, right now, at the most impressive it's ever been, it has this fundamental flaw.

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

#267

Earlier quoted context omitted.

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.

I would not and do not trust them to do this in cases where I care about the accuracy of the output.

If you care about the accuracy of the output, don’t read news in the first place? I think you’re trumping up the impotence of this use case.

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

#268

Earlier quoted context omitted.

> Given that the choice of which articles to write is incredibly biased to begin with this approach does not seem effective. Selection bias is a given. You always have to keep that in mind. But when you actually want to read a specific article, summarizers are useful. For news and general population content, debullshitifiers could come in handy too. Point being, the texts are not random . There's some nugget of valua…

I’m not arguing summarization is not useful, or stripping the various sources of noise you listed. “Debullshitification” reads as de-biasing which is not what you just itemized. My point is rather that Fox News+LLM (as an example) is still biased but would appear/may be incorrectly presented as unbiased to a reader not acutely aware of selection bias which is probably not something an average reader is well informed…

No, you’re applying a specific meaning to an inherently nebulous term, debullshitification.

And honestly, I immediately knew what that meant when I read it. My preferred news source, which isn’t horrendously partisan, still has…exactly what I’d call bullshit. If that’s removed, I’ll get more bang for my buck in reading it, and that both provides immense value, and something that I’d call “debullshitification”, whilst working purely from the articles provided.

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

#269
Great idea. I wish the teasers were complete sentences, not truncated. I also wish headers and teasers were complete and not click-baity. A reader should only need to click on the article for more details, not to figure out what it is about.

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

#270

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.

> underreporting of crime makes crime rates meaningless

Well, if they can present the rate of crime underreporting, and how it has changed over time, they're welcome to add it to the graph :)

Post reply on HN