HackerTrans
トップ新着トレンドコメント過去質問紹介求人

margotli

no profile record

投稿

Show HN: I built a tool that helps predict HN front page success

wannalaunch.com
26 ポイント·投稿者 margotli·2 か月前·23 コメント

What predicts Show HN front page success? I analyzed 73k recent ShowHN posts

wannalaunch.com
3 ポイント·投稿者 margotli·2 か月前·9 コメント

[untitled]

1 ポイント·投稿者 margotli·3 か月前·0 コメント

Show HN: Open-source AI data generator (now hosted)

metabase.com
39 ポイント·投稿者 margotli·10 か月前·0 コメント

コメント

margotli
·2 か月前·議論
Well, the model can suggest patterns, but everyone is responsible for what they post.
margotli
·2 か月前·議論
That is true and I agree. I guess in this case the "success" I meant was hitting and staying on the front page so that more people can see your project.
margotli
·2 か月前·議論
That's my second try, my first post actually got shadowbanned, so I had to change the domain (it was originally GitHub) and the title wording for this one.

There are still a lot of random factors on HN, so nothing can predict things perfectly, but I like that the model gives you feedback based on real data behind it.
margotli
·2 か月前·議論
Haven't used anything - I'm as impressed as you are.
margotli
·2 か月前·議論
That what surprised me too, also Saturday turns out working just fine. My explanation would be that on weekends there is less competition for the attention. Even with less people on the platform, it's still easier to get noticed.
margotli
·2 か月前·議論
Ha-ha, all good - I can see your comment.
margotli
·2 か月前·議論
I used a dataset from HuggingАace to analyse all Show HN posts for the past 3 years. Here is what influences if the post gets on the front page.

- Niche technical topics have the highest viral rates (Rust, Postgress, Lua, etc) - Open source tools are the top performing category with 13.9% viral rate - "I built" outperforms "We built" - Sunday noon UTC has the highest chances to hit the front page - Titles with a parenthetical work much better that those without.

More insights in the blog article.
margotli
·3 か月前·議論
I guess because tokens is the only metric that ""reflects" how high your AI adoption is. So especially in tech industry, if a company pushes for AI adoption, the token usage is the only proxy metric you have.

Agree that it's absurd though.