Hacker News new | past | comments | ask | show | jobs | submit | visekr's comments login

i was gonna say the same - as my post got sunk into oblivion after hitting second page


Loveee that idea.

Would be cool to even have designated groups so you could filter by left wing, right wing, international, etc.

Gonna work on this after I optimize the codebase


ah thanks : )

yes - not sure what detail you want but I'll try to be thorough here.

Tech stack is React, Next JS, Radix UI lib, Tailwind, Firebase for database auth and cloud functions, Vercel for deployment, OpenAI for article classification, WorldNewsAPI for news.

Cloud Functions run at different intervals, I have one that runs every 30 minutes (recent news), 12 hours (weekly news), 84 hours (monthly news) and 168 hours (quarterly news). This is a big WIP

On a cloud function run it fetches articles from newsAPI, this search is done with a mix of keywords that determine if its related to the current administration, then gets filtered down to 'credible' sources (listed in a comment on this thread). The content of the articles that pass these filters get send to gpt-4o to be classified for relevance (is it an action of the administration / related) if it passes that >70%, the ai determines if it matches any of the 14 steps of facism, and will add a direct quote / impact / summary of why it matched that step, and finally will get added to DB and displayed on the site.

In terms of development - heavy use of Cursor IDE, and start with v0 by Vercel which is why I was able to get this up and running within ~3 days. Although the codebase looks disgusting rn


I'd love to tap into that eventually! Right now I'm using an API that give me a dump of like all articles and I filter that through a list of 'credible' sources. I'm not the most educated about what are good sources for this but this is my current one. (it also shows on the site under - 'what is this') Would loveee feedback on this list.

Allowed Sources Major Wire Services (1.0) Reuters, AP, AFP, Bloomberg Top US News (0.9) NYT, WaPo, WSJ, ProPublica

Conservative Media (0.7-0.8) Fox News, National Review, Washington Times, The Dispatch, Washington Examiner, RealClearPolitics, Reason

Progressive Media (0.7-0.8) Mother Jones, The Nation, Democracy Now!, New Republic, Jacobin, Truthout, Slate

International (0.8-0.9) BBC, Guardian, FT, Economist, DW, France24, Al Jazeera

Fact Checkers (0.9) FactCheck.org, PolitiFact

Major Networks (0.8) NPR, NBC, CBS, ABC, CNBC

Digital Media (0.7-0.8) Atlantic, Wired, Axios, USA Today, Time


Putting the openly biased/partisan (and more often than not intentionally deceptive) media sources at the same level as major networks, digital media, and the low end of international media seems like a mistake to me. It lends an undeserved level of credibility to the extremely biased sources, and at the same time unfairly conflates the other media sources with them.

So does the Digital Media group as a whole - it seems overly reductive, and the sources are too varying in quality/reliability to be given the same weight. And does something like Time really fit in there, considering they've been print media for the vast majority of their existence?

(Love the project overall, though! Thanks for creating and sharing.)


>> Would loveee feedback on this list

OK, my feedback is that it is a very left leaning list of sources. I use a site, https://www.allsides.com, that does media bias ratings and rates sites from -6 (high left bias) to 6 (high right bias), and outside of the ones you have listed specifically listed as "Conservative Media", every site that I could find was negative, other than the FT which was listed as "Center" with no numerical rating. Yes, even the WSJ, although that was WSJ news rather than opinion, opinion was slightly right.

Here's the list I got, I had to make some choices on what to use, "ABC" for example can refer to different things.

The Nation -5.00

Slate -4.50

Democracy Now! -4.00

Mother Jones -4.00

New Republic -4.00

Jacobin -4.00

The Atlantic -4.00

Guardian -3.50

AP -3.10

AFP -3.10

Wired -2.75

Time Magazine -2.30

TruthOut -2.00

Politifact -2.00

ProPublica -2.00

NPR -2.00

CBS News (Online) -1.50

FactCheck.org -1.60

Washington Post -1.63

NBC News Digital -1.80

New York Times -2.20

Al Jazeera -2.30

Bloomberg -2.40

USA Today -2.00

Axios -1.70

ABC News (Online) -1.42

Economist -1.40

CNBC -0.90

Reuters -0.89

BBC -0.80

WSJ -0.20

FT ? Rated as Center with no #

RealClearPolitics 0.16

Reason 0.28

The Dispatch 2.00

Washington Times 2.00

Washington Examiner 2.30

National Review 2.50

Fox News (digital) 3.88

If you're trying to build a left leaning media bubble, you're doing a pretty good job. I would be curious to see results from the opposite, choose a few examples of "Liberal Media", and populate the rest of the list with sources that were rated as leaning right.

And I'm sure some people will disagree with the allsides bias ratings. There's no way to be completely objective on something like that. They seem pretty believable to me, but I'm not watching the same movie y'all are.


If a website rates the economist as left leaning it's maybe a sign of the bias in the evaluation and how much the discourse has been pushed to the right (in the US at least)


It's a reasonable take on the actual political climate in the US. Trump has a 50% approval rating, the border between approving and disapproving of him is mathematically (approximately) the political center.


Are you comfortable sharing which API you use?


of course! WorldNewsAPI - wasn't my first pick but was the most affordable for me, but i like it so far, no complaints!


Good feedback! ill work on making it a bit more clear.

as for the time-dependance / algorithm, good question .I'm still working on tweaking it, right now recency has a 30% weight. I just started this last thursday so im quite unsure how things will change / look on the site over time and what makes sense for a half life / decay of an article.


You need to work on your classification algorithm. Classifying anti-Trump mass media articles as "controlled mass media" is just embarrassing.


Thanks! and this is actually one of the things on my list. Still noodling on how to do this effectively and efficiently, since I want it to follow my same process of filtering through gpt-4o, and running 10 years of data through that could cost me.

But yes love the idea : )


This is really cool - I've had a halfbaked idea of a visual code editor for a while and this really solidifies my concept. if anyone wants to work together on it lmk : )


Glad you think so! =)

I'd love to chat with ya. Do you see my email? Feel free to email me! If not, reply here with whatever you'd prefer to chat with and I'll get back to you.


Sent!


Hi HN : )

Spent the last few weekends building this idea out.

After moving into a new place and discovering my upstairs neighbors being louder than I expected, I figured it'd be useful to check a spot's noise levels before moving in.

Enter MindTheNoise—just drop any address, share the noise levels, what’s causing it, and any other helpful info.

Let me know what you think

- Ryan


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: