Hacker
AI
title performance prediction
SHOW HN2020
How HN took it
2 positive, 20 neutral or asking, 2 mixed, 10 critical, out of 34 comments about the project. Thread score -0.23.
Idea: 0 for, 4 againstExecution: 0 for, 3 againstPerformance: 0 for, 3 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Fun idea that makes for entertaining experiments
From 3 comments
Great idea, Love things like this! Competition time - Can anyone come up with a title better than "Rust"? Edit: I've beaten "Rust" by putting in the title " ". Can anyone beat…
Closi on HNI love it when people come here and shit about old data sets or other bs. Gj op! Haters going to hate and makers going to make.
numbman on HNA: "Show HN: I built a decentralized data set index" [1] B: rust => B is 66% better. Damn it, I should have used rust! Anyways, great project. Bookmarked! 1: Shameless…
timdaub on HN
Objections
Model trained on 2006-2017 data is outdated
From 1 comment
> dataset that contains all stories and comments between 2006 and 2017 That seems rather old data for a tech community?
Gys on HN
Input encoding of characters as numbers loses meaning
From 2 comments
> The title is transformed it into an array of numbers between 0 and 1 (each character is a number) and this data is fed (along with the number of points) to the neural network.…
NumberCruncher on HNConverting text to numbers via individual characters destroys any semantic meaning to the input. Which is why no advanced NLP tools will do such a thing. Basically, what they…
timy2shoes on HN
Model outputs are close to random; rust scores worse than random strings
From 1 comment
``` const randAlphaStr = length => String.fromCharCode( ...Array.from({ length }, () => 97 + Math.floor(Math.random() * 26)) ); const pitRustAgainstRandomFourCharAlphaStrings =…
oefrha on HN
Predictions can feed back into the training data and skew results
From 1 comment
Please don't use this in practice. It's trained on a dataset that it then ends up affecting, so we could end up with some really weird situations.
wizzwizz4 on HN
Requests
Use the current front page as context for ranking
From 1 comment
It's also strange because what they've trained is essentially a recommender system. However, at inference time you're not trying to rank 2 different articles, but the same…
eugenhotaj on HN
Allow a short summary alongside titles on HN
From 1 comment
I'd just like for HN to have the ability to add a 1-2 line summary with the title - a lot of titles feel like clickbait.
johnny_b_g on HN
Questions
How many titles were tested to get the reported accuracy
From 1 comment
I want to know how many titles they A/B tested to get this one.
jonplackett on HN
Is it built with OpenAI
From 1 comment
Lol! Is it build with OpenAI?
Michael_Sieb on HN