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

61–70 of 348 posts

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

#61

Post by TySchultz »

powersnail wrote: post #50

I've also been thinking about processing news with LMs, but from a different angle. One big complaint I have for reading news through RSS, is that there's no natural hierarchy/priority to the news. There's no front page, no headline, no size in RSS feeds. Given the way news agencies generates those feeds, there are _tons_ of repetition, tiny updates, some insignificant one-liner interview about some significant event…

I had nearly the same idea as you around surfacing what is "important" vs just a large list of RSS articles.

The main differences compared to what you are thinking are two things. One for the `Significance of the event` I've used the number of publishers talking about that event. So more publishers == more important. Two, I've done this in a daily fashion instead of a weekly report.

I can also confirm that the LM has the capability to do at least a days worth (2500+) of articles. I would doubt its capability to produce an entire article but it does a great job at a small summary.

Here is the link if you wanted to check it out. https://apps.apple.com/us/app/quill-news-digest/id1669557131

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

#62

Post by aquaVitae »

xtracto wrote: post #47

Thanks for doing this. This is something I've been looking for since ChatGPT was unveiled generally. I wish Feedly or a similar RSS/News-aggregator would add a feature like this ... it would make so much sense.

We plan to implement RSS support as well, so please stay tuned. Thanks for the support.

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

#63

Post by sureglymop »

yamazakiwi wrote: post #45
dubcanada wrote: post #38

Earlier quoted context omitted.

What a weirdly aggressive attack... Either I'm selfish and have a lot of biases or I'm lazy. Could it not be that as a person with an interest in AI and general technology I am wondering if there is any detail on what does an "AI" look for to determine a "sensationalist" title and how does it "desensationalize" it? I have scanned the twitter feed and the app and just wondering if there is anything on how it works. Th…

I'm not trying to attack you, I was dissecting your intentions, which I'm now noticing came off as super rude and I apologize for that. But let's be frank... It's clear through your verbiage that you were either thinking about this politically or were actually just curious as I stated in my previous message. I never said you were lazy, there are many reasons why you might not be able to try out the product right now…

I read the OPs comment seemingly in a completely different way than you.

To me, it's just a comment asking how it may work (technically). Pretty normal to ask that on HN. The persons feelings or intentions aren't reflected in the comment and I think aren't relevant to the question either way.

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

#64

Post by asoneth »

The headline style reminds me of Matt Winkler's "Bloomberg Way" which specified headlines that summarized the article into a single line, see: https://wildtech.mongabay.com/wp-content/uploads/sites/20/20... or https://www.optionsbro.com/wp-content/uploads/2017/12/Bloomb...

I'm not sure if they always achieved that, but it was at least a goal for readers to be able to skim feeds to understand what was going as quickly as possible. Such a policy was feasible because the readers were paying customers as opposed to web news which are often funded by advertisers or worse.

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

#65

Post by torresmo »

tikkun wrote: 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…

I am looking forward to a tool to summarize a 10 page long Terms of Service into a list of points about what I really need to beware of. Same for legal contracts.

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

#66

Post by chankstein38 »

I think this is an amazing idea! The only flaw I see with it is that without the sensationalized headlines I read through going "Oh that doesn't matter, that doesn't matter either" etc haha I haven't found an article that sounds interesting in a few scrolls.

I mean, it's great because it's accurate. Half of the "news" we're fed is sensationalized so we'll click on it and it's really nothing but it gets us riled up about something that is effectively meaningless to us. This just brings reality to the forefront and makes me realize I don't care about the news lol

Thank you though, this is awesome!

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

#67

Post by yamazakiwi »

sureglymop wrote: post #63
yamazakiwi wrote: post #45

Earlier quoted context omitted.

I'm not trying to attack you, I was dissecting your intentions, which I'm now noticing came off as super rude and I apologize for that. But let's be frank... It's clear through your verbiage that you were either thinking about this politically or were actually just curious as I stated in my previous message. I never said you were lazy, there are many reasons why you might not be able to try out the product right now…

I read the OPs comment seemingly in a completely different way than you. To me, it's just a comment asking how it may work (technically). Pretty normal to ask that on HN. The persons feelings or intentions aren't reflected in the comment and I think aren't relevant to the question either way.

I think it's the word "Exactly" in his sentence that changes the meaning away from "I'm intellectually curious" for me. I'm just reading between the lines but the op can change their intention as they please and deny so whatever I say at this point is irrelevant and it's likely I was being too cheeky.

Wouldn't someone who was intellectually curious just ask: "That's interesting, I wonder how it works?" and not: "What does desensationalized exactly mean?" which is overly negative. Incidentally, I'm being accused of being negative for pointing that out.

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

#68

Post by gnicholas »

Love the idea, the name, and the app logo. I tried it with a CNN article and found that the output was a bit too summarized. It would be nice if users could specify if they want no summarization (just desensationalize) or if they want summarization included (and possibly to what degree).

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

#69

Post by kmod »

I built something that summarizes hacker news discussion pages for me, and I have been very pleasantly surprised how much nicer it is to read "angryuser1 and angryuser2 got into a heated discussion" than to actually read the discussion. Forcing everything into the neutral gpt voice has greatly reduced the emotional valence of my HN consumption

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

#70

Post by akomtu »

Modern "news" is a lot like sewage padded by corn fructose syrup and wrapped into shiny colorful pills to fool the mind. It's true that the pills have useful elements in trace amounts, but if you start harvesting them from the pills, you'll get poisoned. Your LM just removes the deceptive shell, but the pill's contents remain the same. I think it would be better if your LM identified and highlighted lies and deceptions in news articles. Most of them will be all in red, but that's the goal: give users an idea what they are reading. For example, the prompt for your LM could be: "for every statement in this arricle, mark it in red if it's a lie or an unsubstantiated claim, mark it in purple if it's appeal to emotions, mark it in green if it's appeal to authority" and so on. I doubt journalusts will be able to outmaneuver LLM trained on every book in the internet. (journalusts to distinguish from true journalists, that are exceedingly rare today)
Post reply on HN