Comment by Triphibian | Hacker News Reader

Comment by Triphibian | Hacker News Reader

This is interesting, but it seems like it is tracking stories with similar headlines and that's not always how news propagates. Frequently a blogger will read an interview, select an quote from the interview and write a new headline around the quote they cherry picked. It used to be common practice to link the original source, but that always doesn't happen.

I have long thought that search engines, news aggregators and social media companies have a journalistic responsibility to favor the original/primary source of every story, but things have not worked out that way. If you can manage to truly develop something like this it would be a valuable tool for rewarding the work of reporting over SEO.

Anyway, please consider that headlines and time stamps do not tell the entire story when it comes to sourcing.

For example: Your website offers this story (https://hotspotatl.com/6587626/dr-jackie-married-to-medicine...) as first to publish. But right in the text it cites another website BOSSIP as the source of the interview.

Also: there doesn't appear to be a way to link results from your website.

> I have long thought that search engines, news aggregators and social media companies have a journalistic responsibility to favor the original/primary source of every story

This is complicated somewhat by the few that take an already-circulating story and then add their own actual research rather than just rewording and opining.

Currently I'm using Snowflake’s Arctic embedding model on the whole story not just the title, to cluster stories. There are still some issues, but its not as simple as looking at title publish date.

Yea, I need to do some work on improving first to publish... currently I'm relying pretty heavily on the published date provided in the story itself, but sometimes that is wrong and makes it look like a later publisher was first to publish.

not linking primary sources is one of my biggest pet peeves with modern ad-driven “journalism”.

e.g. the recent Mark Kelly story, I went through many articles trying to find a link to the actual video of what he said. couldn’t find it

headlines with “[person said X]” tend to be bullshit

Go hunt down the lineage of the “AI water use” articles floating around.

It’s all circular.

I don’t know how one is supposed to trust any of the media at this point. Especially “reputable” ones that are just as guilty of circular nonsense as anything else.

If you don’t follow the media, you are uninformed. If you follow it, you are misinformed.

Reply on news.ycombinator.com