Building a new kind of news site, featuring updates from primary sources.

We're constantly pulling info from official sources, and using AI to group and summarize into stories, and continue to share reporting from trusted, vetted journalists.

The result is news with the speed and breadth of getting updates straight from the source, and the perspective and context that reporting provides.

Still ramping up, but I'd love to hear feedback:

https://www.forth.news

Need is valid. The site is showing mostly flood watch warnings - maybe cluster topics? Also don’t mess with the scroll bar - maybe the ads are doing it, but it froze and wouldn’t move down for a while.

Thank you -- yes, the non-signed in front page needs some work. There's a lot of flood warnings, but if you choose topics with an account it should be a better experience.

And thank you for flagging the scroll thing. I hadn't seen it, but will check.

Didnt quite get this - if the only value prop is getting updates straight from the source (trusted/vetted journalists), what use is AI here, except for summaries perhaps?

AI isn't really the draw, it's more of a tool that helps on the backend.

That said, it's both combining various updates into a cohesive timeline of a story, writing the summaries, and assigning it an urgency level which helps in sorting and some other tasks.

Looks good so far. The AI summary button is nice but hard to distinguish from the background.

V cool, this is a perfect llm use case

thank you -- great to hear!

But you're not doing micropayments, you're using metered billing. There's a big difference.

For one, you have a request. The answer isn't going to be anywhere else. Sure, you can't be guaranteed the quality in advance, but you are guaranteed to not have an answer without submitting the request. This doesn't work in a field where so many see news as commoditized, and can just get a free article or headline elsewhere.

Micropayments have been tried over and over (see https://www.niemanlab.org/2023/08/the-poster-child-for-micro...)

Some of this issue is the nature of news. With an LLM, the providers just run the infrastructure anyway, and your request is routed to it. They develop new models constantly, and deploy. News does not work like this.

If you have to grab someone's attention to read an article, that's an incentive structure that creates clickbait and other things people hate. You may offer a headline, but that is very often the only part of the story people care about. (Oh, Robert Duvall died? That's sad. But I don't need to pay anything to read anymore -- I already know the story!)

It also does nothing for the piracy that is so rampant -- especially on this site. How many people post archive links to articles with paywalls? Would that stop? Getting a fraction of a cent or so before someone else copies the article is absolutely not a business model.

Very old and needs an update/refresh, but https://www.jaredwiener.com

Does it have value to the customers using/paying for it? Would someone want to acquire it?

Good point. Yes, very much so to value point. I imagine no to acquisition.

Do any of your customers find enough value in it to take it on themselves?

The food pyramid was phased out in 2011: https://www.politifact.com/article/2025/nov/07/food-pyramid-...

You can't phase out common "knowledge"!

True. But you can stop recommending bad science. The original food pyramid was an industry wish list.

This is the first .gov website I've seen that does not list any sort of agency, branch of government, commission, whatever, that's behind it.

Yes, I see the National Design Studio built it -- but presumably they aren't the ones writing nutritional guidance. Is this FDA? HHS?

Nutritional guidelines are developed by USDA.

This newest iteration appears to have had input from HHS under RFK Jr: https://www.nbcnews.com/health/health-news/us-dietary-guidel...

My point really was that it seems odd that this information isn't readily available on the website. Why hide it?

This also appears to be from USDA, as per their other website with the same info: https://www.dietaryguidelines.gov/

Free Law Project also has this open source tool to detect bad redactions: https://github.com/freelawproject/x-ray

Why would you have anything for the backend in an APK? Wouldnt that be an app, that by definition runs on the client?

Most frameworks also by default block ALL environment variables on the client side unless the name is preceded by something specific, like NEXT_PUBLIC_*

> Most frameworks also by default block ALL environment variables on the client side

I’ve been out of full stack dev for ~5 years now, and this statement is breaking my brain

Why would you have anything for the backend in a browser app? Wouldn't that by definition run on the client?

These kind of node + Mobile apps typically use an embedded browser like electron or a builtin browser, it's not much different than a web app.

Verizon's status page says it's "multiple fiber cuts"

They have job postings that include NYC-based network operations engineers. https://www.txse.com/meet-the-team#careers