zlacker

>>t0bia_+(OP)
I am European and see another US news oriented site which ironically is not "minimalist" from my perspective. It is (to me) littered with US domestic concerns. My point is that _minimalist_ is highly subjective and a pretty huge promise from a site.

But kudos to the effort and the idea of keeping news small is a most noble cause

>>finnjo+G81
Agree, as a Canadian, I also find that today too many US-centric news made the cut, but often it's not the case. Here's a recent issue covering different topics and not mentioning US at all: https://newsletter.newsminimalist.com/p/tuesday-april-25-3-m...

>>yakhin+I91
Oddly enough in the 'least significant section', with scores <0.5, it's nearly all Daily Mail articles focused on the UK.

Also, the second to last least significant article seems to be incorrectly categorized: "Regenerative medicine has come a long way, baby"

Which is actually a serious look back at the advancements over the last quarter century, hardly deserving the second to last position.

It seems like ChatGPT is ranking them not based on actual content significance but presumed significance of the headline. (Which would also make sense technically as ~1200 headlines is about the max context length of GPT-4).

>>Michae+CE1
Nice catch. Just checked that article — it actually got rating 2.8 just based on the news content, but the source credibility 1/10 brought it down to 0.3.

I don't think it's fair, I think ChatGPT hallucinated that it's a tabloid.

Not sure how to fix this. I don't want to adjust sources credibility manually, that will introduce too much bias. My hope is that OpenAI will update ChatGPT with newer data and I could rerun the credibility evaluation.

>>yakhin+lS1
So how exactly is the credibility score determined? Is it just asking "On a scale of 0 to 10, how credible is this source?"

>>starkp+Yh2
It's a bit longer, but that's the gist of it.

I just realized, for that particular news article about Regenerative medicine it was my mistake all along. I asked ChatGPT to give unknown sources a score of 1 and completely forgot about. I think that's what it did.

For now it marked only 8 sources as unknown out of 1700.