Detect GPT

Detect GPT

A Chrome extension that spots AI-generated content.

4.5
4 reviews

355 followers

Detect GPT scans the content of the webpage you are viewing and analyzes it to identify if any of the content has been generated using the GPT language model.
Detect GPT gallery image
Free
Launch Team

What do you think? …

thomas.io
Hey hunters, As more and more content is being generated by GPT, I thought it would be useful to be able to identify whether something I read was written by a human or not. So, I created a Chrome extension that scans the content of a page and changes its color if it detects AI-generated content. It's free to use, so give it a try and let me know what you think!"
Rhymer Espinosa
@tompec Congratulations on this big step / launch. Really rooting for your success.
Shon Paunan
@tompec Cheers to you, congratulations'
Brian Roach
@tompec beat me to it! I was about to launch mine this weekend (had back surgery yesterday). Excited to give this a go! Congrats on the launch. 💪
Awee Gee
@tompec Congratulations! Continue your excellent work!
Puneet Kohli
This is amazing if it actually works as promised and is probably something even OpenAI would like to have (and potentially buy from you). Could you share a bit of the behind-the-scenes magic? I know this is an open area of research and part of it involves actually having an equivalent of a “cryptographic blueprint” of the model itself, which obviously, as outsiders we don’t have… so really really curious. *praying to god that the answer isn’t that you’ve trained a classifier on GPT’s generated outputs*
thomas.io
@puneet_kohli It's actually using a detector built by OpenAI https://github.com/openai/gpt-2-...
Mustapha Ajermou
@tompec does it detect gpt3 and beyond content?
thomas.io
@mustapha_ajermou1 Yes it works pretty well with GPT3 and ChatGPT so far.
Shushant Lakhyani
This is a must-have in a world where the future seems like there will be a lot of AI generated content. But still, don't you think people can cheat this extension?
thomas.io
@shushant_lakhyani this isn't 100% accurate, but this is good enough to know when content is not fully human written