- Learning Intelligence
- Posts
- Get GPT-4 Vision in Your Phone Camera
Get GPT-4 Vision in Your Phone Camera
I programmed my phone so it can automatically take a screenshot when I tap the back of my phone twice, send it to GPT-4, and get a description of it.
All in seconds!
To be able to follow this tutorial, you’ll need an iPhone (Shortcuts) and an OpenAI key. Here I have a quick video on how to get a key:
Getting an OpenAI API key.
Next, you’ll need a Shortcut, which will set up everything for you. You can just add this one: https://www.icloud.com/shortcuts/6aaa82583c14499499103014c2177940
Once you add the Shortcut, you’ll need to enter your OpenAI key inside the Shortcut where it says “Text”.
You can also modify the prompt if you want.
To be able to double tap on the back of your phone and access the Shortcut, you have to:
Go to Settings > Accessibility > Touch, and tap Back Tap. Next, tap Double/Triple Tap. Lastly, select your Shortcut name.
Now you can open up your camera, aim for what you want a description of, and tap twice or three times on the back of your phone to get a description of it.
I hope you enjoyed this tutorial. You can follow me on X/Twitter for more: https://twitter.com/dr_cintas
Also, if you would like to support me, I would highly appreciate it if you subscribe there too!
Cheers,
Dr. Cintas