Google has a new API that tells you how "toxic" text is, h/t @taoeffect 

It's 🤣 to poke around and see what biases the system picked up from the training data. 😰 to think about actual applications, though.

Maybe it's not fair to try single words when the model is designed for use on comments, so let's try things that could be entire comments 😇

Looks like this (or something like it) made it into production?

Google Cloud Vision API:

Black hand holding thermometer = hand gun
White hand holding thermometer = hand tool

You can follow @danluu.


Tip: mention @threader_app on a Twitter thread with the keyword “compile” to get a link to it.

Enjoy Threader? Sign up.

Since you’re here...

... we’re asking visitors like you to make a contribution to support this independent project. In these uncertain times, access to information is vital. Threader gets 1,000,000+ visits a month and our iOS Twitter client was featured as an App of the Day by Apple. Your financial support will help two developers to keep working on this app. Everyone’s contribution, big or small, is so valuable. Support Threader by becoming premium or by donating on PayPal. Thank you.