Hacker News AI Detector

I dont get why lol for what

How do you validate the accuracy of the AI detection?

Has this been getting harder and harder?

is this just for fun?

This is interesting!

Nice one, I am read a lot articles on Hacker News

Really interesting use case! The stat that 16% of Hacker News front page is AI-generated is eye-opening. Would love to see a trend graph showing how this percentage has changed over the past year.

Thats cool, can you do it for news in general?

it's interesting project, it similar to check keyboard input or hand input

This is a much-needed tool for maintaining content integrity on platforms like Hacker News. Since you're offering this for free, do you have a plan to monetize the API or the detection data in the future?

Well, in today's world 99% of content is AI. But what the point of value of this product is? How can I use this to make some value for myself? Or it's like a fun project?

Quite a fun project, but how do you take into account that really technical docs even if human written often get flagged as AI-generated?

Quite a fun project, but how do you take into account that really technical docs even if human written often get flagged as AI-generated?

Interesting angle. A confidence score plus a short note about likely false positives on satire or edited posts would make the result much easier to trust and share.

Hey! 👋 As an avid reader of Hacker News, I've started to notice some posts being blatantly AI-generated. Sometimes, there would be comments accusing the author of generating AI slop. I started to wonder, how many posts are actually AI-generated these days? I started collecting data and labeled the posts using AI text detection tools. This page mirrors the Hacker News front page, with posts labeled either Human, Mixed, or AI-Generated.

You could also create an AI detector for open-source projects.

interesting project, pretty cool

Cool, is this work or not?

This is pretty cool!

It's hard even for certified AI detecting algorithms to sometimes differentiate between AI and human. Do you have any mechanisms in the algorithm that tries to fix that?

This solves a real workflow gap.