Coming up with useful applications of Machine Learning can be an exciting and complicated problem. Sure, I can do the same linear regression problem everyone does, with the same data, but if I’m not excited about what I’m creating, how can I expect anyone else to be interested?
Then I got the idea, what about NSFW detection for client and server! This could cut down on work for teams, as well as provide a high-profile project for others.
Since creating the NSFW model, throngs of people have tweeted, and shown up to add pull requests. I’ll even be Keynoting in Italy, to review the project.
One common request, a lot of people keep asking for the training data. I’m both entertained and engaged in all the interactions in this project. Never would I have assumed so many people would help me learn, challenge me to grow, and take interest in my project.
Because of this, I’ve documented the entire project here: https://medium.freecodecamp.org/how-to-set-up-nsfw-content-detection-with-machine-learning-229a9725829c
And released a JavaScript library here: https://shift.infinite.red/avoid-nightmares-nsfw-js-ab7b176978b1
What’s your cool project?
Share the thing you’re hacking away on in your spare time! The thing that you want to share with the world, and no 9 to 5 will stop you?

I think the first step is to finish a game on Pico-8, then to finish a game using Phaser or some other Javascript library. Once I’ve done that, I’ll have a solid foundation for an engine I can script with whatever language I design.