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

Post by ChatGTP » Thu, May 11, 2023, 11:55 PM UTC

gnicholas wrote: post #79

chankstein38 wrote: post #66

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 ab…

I think the issue here is that we've been fed a high-sensationalism diet, so our brains are acclimated to in-your-face headlines. Perhaps if we detoxed our brains a bit (by using this app exclusively for a week or two), we would be able to recalibrate our expectations for what seems "interesting". This is sort of like how you recalibrate your tongue to a low-salt diet if you stop eating salty food for a few weeks.

Post by TheCaptain4815 » Fri, May 12, 2023, 12:00 AM UTC

haldujai wrote: post #167

TheCaptain4815 wrote: post #166

Earlier quoted context omitted.

This will be a combination of numerous fine-tuned models, def not using a default LLM. A bold statement but one I believe is correct. Even Elon Musk, the richest man on the planet, believes this. Guess we'll see, my main priority is ensuring it's accurate and as unbiased as possible. It must work on every news site, both left and right wing.

I don’t think it’s a given that finetuning address pretraining bias, most LLMs you would have access to are trained on very similar and biased corpora, see any Anthropic or OpenAI alignment paper. It’s conceptually possible for extensive finetuning + MoE to work accurately enough for this premise to be feasible but it seems incredibly unlikely with what’s available today. In any case, using a non-explainable AI model…

Post by pessimizer » Fri, May 12, 2023, 12:01 AM UTC

haldujai wrote: post #142

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

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?

Post by jeremy_wiebe » Fri, May 12, 2023, 12:16 AM UTC

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.

Post by haldujai » Fri, May 12, 2023, 12:19 AM UTC

TheCaptain4815 wrote: post #203

haldujai wrote: post #167

Earlier quoted context omitted.

I don’t think it’s a given that finetuning address pretraining bias, most LLMs you would have access to are trained on very similar and biased corpora, see any Anthropic or OpenAI alignment paper. It’s conceptually possible for extensive finetuning + MoE to work accurately enough for this premise to be feasible but it seems incredibly unlikely with what’s available today. In any case, using a non-explainable AI model…

I’m thinking a multi model approach from classification of a “bias” to the rewriting. In a perfect world I’d also incorporate a database of scraped tweets and one day video dialog. Idk about you, but I’d love to see the most racist tweets from a NYT or WSJ journalist, along with the articles they’ve written, a score associated with their content, etc.