I made a similar project where all news is ranked by significance on a scale from 0 to 10.
Because the significance is determined by an LLM, it surfaces many stories that are usually missed by major media.
182 karma · joined September 3, 2022
---
meet.hn/city/ca-Vancouver
Socials: - github.com/yakhinvadim - x.com/yakhinvadim
---
Because the significance is determined by an LLM, it surfaces many stories that are usually missed by major media.
But what you're asking sounds extremely close to what I made: https://www.newsminimalist.com/
If you want fewer stories (by default it shows about 25 a day), adjust the slider to a higher significance threshold.
I think there will always be some hallucinations until they're solved on a model level, but I'll also try to nudge AI now to be more precise with the headlines.
I think it worked quite well, there's only about 10 headlines a day (out of 15k+) that get a significance rating higher than of 5.5 out of 10.
It also helps avoiding the overfocus on western issues and actually learn what's happening around the world.
Three men occupy table without eating at busy food court
A video taken by a Singaporean Stomper shows three men playing games on their mobile phones while seated at a dining table in a crowded food court. The group did not have any food or drinks on the table, and despite the lunch crowd, they did not give up their seats to those waiting for a table. The incident occurred at the newly-opened Sinfoodie food court at Tai Seng Street, which is known to be very busy during lunch.
https://www.newsminimalist.com/articles/d8a34b64-3486-4a45-8...
A couple recent examples:
[Significance 6.7] China outlines ambitious space strategy to surpass US by 2050 [1]
[Significance 5.9] Scientists explore ocean floor findings that could reveal oxygen on other planets [2]
[1] https://www.newsminimalist.com/articles/china-outlines-ambit...
[2] https://www.newsminimalist.com/articles/scientists-explore-o...
It's available via RSS too: https://rss.beehiiv.com/feeds/4aF2pGVAEN.xml
I attempted to make a weekly version, but quickly dropped the idea. Over the course of the week articles often became outdated (not just old, but plain wrong).
I found that an optimal newsletter schedule is sending it about every 48-72 hours, depending on how eventful that period was. With this frequency, the articles rarely become outdated, and at the same time it's not too frequent to get tired of.
I was disagreeing a lot with their selection of news, for example one of their recent entries is:
"Two people are killed and eleven others are injured when a bus flips on its side on a highway near Prenzlau, northeast of Berlin, Germany."
My system gave it a significance score of 1.8, so similar news should never get to the main page: https://www.newsminimalist.com/articles/two-dead-and-four-in...
The default feed sorting is done for regular visitors (new first), for evaluating the output you might like the "significant first" more: https://www.newsminimalist.com/?sort=significance
On that list, the ceasefire article is on the second place out of the ~40k articles analyzed.
---
Having more variables is an good idea. I don't have an immediate vision on how to use it in the UI (I want to keep it minimal), but will think more about it.
---
I've been really torn on free trial. I currently offer a refund guarantee, but will add a trial as well soon.
In the beginning I had 3 parameters: scale (number of people), magnitude (degree of change for those impacted) and additionally potential (how likely is this event to trigger downstream significant events).
The point behind including potential was to separate these two events:
1) A 80 year old dies from cancer 2) An 80 year old dies from a new virus called COVID
This worked roughly well but I kept adding parameters to improve the system: novelty, credibility, etc... The current system works on 7 parameters.
---
I never attempted to give LLM all options and rank them against each other.
1) as you said, for me 20k articles is just too much to fit into context window. Maybe some modern LLMs can handle it, but it wasn't the case for a long time, and I settled on current approach.
2) I don't want the "neighbors" to affect individual article ratings. With the current system I am able to compare news spread over months, because they were all rated using the same prompt.
3) I intentionally avoided giving AI examples, like "evaluate event X given that event Y is 7/10". I want it to give scores with a "clear mind" and not be "primed" to my arbitrary examples.
There was a period when I considered switching to an open-source model, but every time I was ready for a switch, OpenAI released a smarter and often cheaper model that was just too good to pass up.
Eventually I decided that the potential savings are not worth it in the long term - it looks like LLMs will only get cheaper over time and the cost of inference should become negligible.
My goal with this project is not to get "true" significance but to have a setup that gets you 90% of the way there: an automated system that finds events that are likely to affect large groups of people or major systems and filters out most of everyday noise.
There will always be false-positives and false-negatives, but I think it's a good starting point and it should slowly get better as models get smarter.
No plans for an iOS app, but my site is a PWA so can be installed and look like an app both on Android and iOS.
"World" includes everything that talks about two or more countries.
"Nation" is a category with news that touch only a single country, not necessarily US. The current feed is very US-heavy because practically everyone (even non-US sources) is talking about Trump.
Keyword blocking is available on premium: https://www.newsminimalist.com/premium#block-topics
Most other aggregators show news based on 1) relevance, 2) upvotes or 3) coverage.
Relevance-based algorithms tend to put reader into a bubble, where the more they read on a certain topic, the more news they see on that topic.
Upvotes-based algorithms usually bring up a lot of clickbait and drama.
Sorting by coverage doesn't really work either, media often just follows people's interests and churns articles on what is "hot".
For example, last summer, a fight between Zuckerberg and Musk was at the top of most feeds based both on upvotes and coverage. Significance-based algorithm didn't even put it in the top 50.
I separate significance from importance (or relevance).
Importance is subjective. News about the health of my family members is important to me, but it is not significant to the world.
Significance is objective. It's about how much the event affects humanity as a whole.
Wikipedia current events page was actually one of the reasons for creating this project! I was disagreeing a lot with their selection of news, for example one of the recent entries is:
"Two people are killed and eleven others are injured when a bus flips on its side on a highway near Prenzlau, northeast of Berlin, Germany."
My system gave it a significance score of 1.8: https://www.newsminimalist.com/articles/two-dead-and-four-in...
I think LLMs are really underutilized as a "judgement tool". A couple similar ideas people reached out to me with were: evaluating which pull requests are more significant in a big repo, or which grant applications have more merit.
The LLMs will always make mistakes, but they could work great as the first filter.
But from what I've seen it's pretty indifferent to "sides", it's more focused on raw numbers of people affected and magnitude of the event.