Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Testing HN titles against a neural network

github.com

Post reply on HN
Print view View original

161–170 of 225 posts

Re: Show HN: Testing HN titles against a neural network

#161

Post by lm28469 »

thaumasiotes wrote: post #123
lm28469 wrote: post #61

I'd argue that titles, as long as they're neutral and accurate, have nothing to do with the upvotes you'll get. This is a perfect example of using data to try to find something that simply doesn't exist or that bear so little weight in comparison to the other variables that you can safely ignore it.

> I'd argue that titles, as long as they're neutral and accurate, have nothing to do with the upvotes you'll get. This is nonsense. If the title is accurate, then it is closely related to the content, and the content has a lot to do with the upvotes you get.

Well yeah, that's exactly what I said. Gaming the system by tweaking your title according to a random github "neural network" won't help you if your content is shit, and if it's not shit the title will be good enough.

Re: Show HN: Testing HN titles against a neural network

#163

Post by atomashpolskiy »

atomashpolskiy wrote: post #162

Finally, I've managed to get a perfectly meaningful and top-rated headline: I've developed a cute Bittorrent client. Upvote, you leisurely butts! Bad: 0.0001 - Good: 0.9999 Not sure, if I should give it a try?

Let's see how it flies

https://news.ycombinator.com/item?id=21524925

Re: Show HN: Testing HN titles against a neural network

#164

Post by mehdix »

trulyrandom wrote: post #160
brutt wrote: post #149

Earlier quoted context omitted.

"I plan to rewrite Linux in Go - Linus Torvalds" Bad: 0.9999 - Good: 0.0001 Rust is 13x better over Go in this benchmark.

"I plan to rewrite Linux in C# - Linus Torvalds" Bad: 0.1897 - Good: 0.7988 Looks like we have a winner.

Clojure scores exactly the same.

Re: Show HN: Testing HN titles against a neural network

#165

Post by holbue »

GistNoesis wrote: post #154

Congratulations on getting first rank on front page. Congratulations on getting your hands dirty and doing everything yourself like computing gradients manually, badly shuffling (non Fisher-Yates), badly js transpose (double swapping), it is a great way to learn. Congratulations on completing a full pipeline, that's the hard part then it just swapping pieces for better pieces. I advise non-technical readers not to at…

Thank you for summarising and thx to OP for publishing his work. The combination of both was a nice opportunity for me (and others?) to learn something from mistakes. :-)

Re: Show HN: Testing HN titles against a neural network

#167

Post by AegirLeet »

According to this tool, HN would not give a fuck about "Windows 11 will use a Linux kernel", "Mark Zuckerberg's lizard tail falls off during interview" or "Google Search to be rewritten in PHP", but "Trump nukes North Korea" would at least be 0.5719 good.

So... I guess the neural network has some learning to do?

Re: Show HN: Testing HN titles against a neural network

#170

Post by atomashpolskiy »

atomashpolskiy wrote: post #163
atomashpolskiy wrote: post #162

Finally, I've managed to get a perfectly meaningful and top-rated headline: I've developed a cute Bittorrent client. Upvote, you leisurely butts! Bad: 0.0001 - Good: 0.9999 Not sure, if I should give it a try?

Let's see how it flies https://news.ycombinator.com/item?id=21524925

Nope, does not work.

More precisely, it received 3 votes, but then someone apparently was insulted by being called a leisurely butt and flagged the topic.

Post reply on HN