Viewing profile — yakhinvadim
yakhinvadim
HN member- Joined
- Sat, Sep 03, 2022, 11:48 PM UTC
- HN karma
- 182
- Public activity
- 98 items
- HN profile
- View on Hacker News ↗
About yakhinvadim
---
meet.hn/city/ca-Vancouver
Socials: - github.com/yakhinvadim - x.com/yakhinvadim
---
Recent public activity
-
comment
Comment #44521273
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 usual…
-
comment
Comment #44521028
Founder here, thanks for the shout out!
-
comment
Comment #44219616
There's https://www.newsminimalist.com/ where 30k news articles per day is ranked by significance, maybe it's what you're looking for?
-
comment
Comment #43897643
I made News Minimalist ( https://www.newsminimalist.com/ ), where I deduplicate and rank ~30k articles a day. For each story the most credible source is picked. Might be what you'r…
- story
-
comment
Comment #42954052
Can't share the full prompt, but I share methodology on the about page: https://www.newsminimalist.com/about
-
comment
Comment #42952812
I'm sorry for plugging my project twice in this thread. But what you're asking sounds extremely close to what I made: https://www.newsminimalist.com/ If you want fewer stories (by …
-
comment
Comment #42952620
Thanks! Good point. 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.…
-
comment
Comment #42951867
I tried to solve this problem by making AI rank the stories by significance and rewriting the news titles in a boring, factual style. I think it worked quite well, there's only abo…
-
comment
Comment #42750872
This is my all time favorite: 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 w…
-
comment
Comment #42750208
It's hard to measure, but I see such stories sometimes, mostly in technology and science. A couple recent examples: [Significance 6.7] China outlines ambitious space strategy to su…
-
comment
Comment #42733197
I don't oppose these ideas, but it's a matter of priorities. There's just many other features and improvements to implement that seem more valuable.
-
comment
Comment #42733157
I think the closest thing to what you want is the newsletter I send 2-3 times a week: https://newsletter.newsminimalist.com/ It's available via RSS too: https://rss.beehiiv.com/fee…
-
comment
Comment #42732948
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 their recent entri…
-
comment
Comment #42732935
Thanks for the deep feedback! The default feed sorting is done for regular visitors (new first), for evaluating the output you might like the "significant first" more: https://www.…
-
comment
Comment #42732856
What you're describing is super close to the first version I had! In the beginning I had 3 parameters: scale (number of people), magnitude (degree of change for those impacted) and…
-
comment
Comment #42732747
Thank you so much! Always glad to see long-time readers. There was a period when I considered switching to an open-source model, but every time I was ready for a switch, OpenAI rel…
-
comment
Comment #42732696
I actually agree that "true" significance can only be estimated in hindsight. My goal with this project is not to get "true" significance but to have a setup that gets you 90% of t…
-
comment
Comment #42732163
Summaries are done for a single article. I think it's better this way — a summary is a clear reflection of an underlying article, where all statements can be easily tracked to a si…
-
comment
Comment #42732101
Yeah, the category names don't convey the meaning behind them very well. There's no intentional focus on US. "World" includes everything that talks about two or more countries. "Na…
-
comment
Comment #42731938
I think the main differentiator for my project is news selection. Most other aggregators show news based on 1) relevance, 2) upvotes or 3) coverage. Relevance-based algorithms tend…
-
comment
Comment #42731815
Good point! I actually have this exact question on about page [0], I'll copy my thoughts from there: I separate significance from importance (or relevance). Importance is subjectiv…
-
comment
Comment #42731799
To your point about raw data - I wasn't expecting there to be so much junk in news. I think I automatically filter out like a third of articles that I get: historic recaps (somethi…
-
comment
Comment #42731741
It's actually available in paid subscription! Users asked for it a lot, mostly to block the recent political drama in US and Ukraine/Russia, Israel/Palestine conflicts. https://www…
-
comment
Comment #42731724
Thanks! I mainly rely on Paid APIs, but additionally go over some RSS feeds for prominent sources that they don't cover. Wikipedia current events page was actually one of the reaso…