Hacker News Reader

If they have the exact same title, perhaps you can skip having a deep neural net and just do a string comparison? Might be sligthtly faster ;)

Finding duplicate stories that have different texts and titles sounds like something you should use AI for

View on HN

I'm definitely thinking of ways to improve it for long-term stories. You're right, fuzzy string matching would do wonders for that, thanks :)

I've used trigram matching of article title strings with some success for comparing similarity of news article. If the strings are greater than .6 they are probably about the same topic.

Reply on news.ycombinator.com