This doesn't look like a print newspaper. Print newspapers are much denser (in general) and have different headline sizes to emphasize the editor's choice of stories. This looks like a corporate blog home page or something. Some people will like this presentation; I'm pretty happy with HN as it is. But congratulations on shipping!
A few years ago, a similar project was posted on HN that I thought was really cool too - E Ink smart screen puts a newspaper on your wall (https://news.ycombinator.com/item?id=22831323).
I made this to experiment with embeddings and explore how different ways of displaying information affect your perception.
It gets the top 100 stories, sends their html to GPT-4 to extract the main content (this was not producing good enough results with html parsing) and then gets an embedding using the title and content.
Likes/dislikes are stored in local storage and compared against all stories using cosine similarity to find the most relevant stories.
It costs about $10/day to run. I was thinking of offering additional value for a small subscription. Maybe more pages of the newspaper, full story content/comments, a weekly digest or ePub export or something?
I liked this for two seconds; then all the pictures loaded in the browser window, and its usefulness to me plummeted. Similar to other commenters, I actually prefer text-only in this context; in particular, the first picture displayed just now was animated, and incredibly distracting.
I would probably use this or at least play with it extensively if not for this "feature." I find that, unlike "real" newspapers, leading images in blog posts and even much larger sites are frequently a net negative (a trend greatly worsened with the advent of AI image generators).
jgrahamc ·8 hours ago
Show replies
pncnmnp ·4 hours ago
A few years ago, a similar project was posted on HN that I thought was really cool too - E Ink smart screen puts a newspaper on your wall (https://news.ycombinator.com/item?id=22831323).
All4All ·6 hours ago
Show replies
nimbusega ·7 hours ago
It gets the top 100 stories, sends their html to GPT-4 to extract the main content (this was not producing good enough results with html parsing) and then gets an embedding using the title and content.
Likes/dislikes are stored in local storage and compared against all stories using cosine similarity to find the most relevant stories.
It costs about $10/day to run. I was thinking of offering additional value for a small subscription. Maybe more pages of the newspaper, full story content/comments, a weekly digest or ePub export or something?
Show replies
eigenhombre ·3 hours ago
I would probably use this or at least play with it extensively if not for this "feature." I find that, unlike "real" newspapers, leading images in blog posts and even much larger sites are frequently a net negative (a trend greatly worsened with the advent of AI image generators).
Show replies