Companion videos

Sharing images with AI: what you can (and shouldn't) upload — companion videos

The article covers what AI vision is genuinely useful for — identifying plants and parts, reading handwriting, sanity-checking diagrams — and what you should think twice about (passports, payslips, photos with strangers in the background). This video gives you four clean minutes of the feature in action so you know what "upload an image" is actually doing under the hood.

Primary pick

4:02

Live demo of GPT-4o vision capabilities

OpenAI

Four minutes of someone holding up a handwritten linear equation to the camera and ChatGPT tutoring them through it without giving the answer. It is the clearest, shortest demo of "the model can actually see what I'm showing it" and frames the use cases the article recommends — handwritten notes, simple math, captured documents — better than any walkthrough we found.

What you should get from this: You can use the camera as an input, showing ChatGPT handwritten work and getting tutoring instead of a spoiled answer.

Watch or know first: None — it's a four-minute demo, not a tutorial.

AI Expert note: Tool interfaces, pricing and product names may have changed. Focus on the workflow pattern, then verify the current UI and settings before using it in real work.

Open video page