One of the most prominent among prolific artificial intelligences, ChatGPTUnfortunately, it is not yet possible to analyze images and videos in the version opened to us. Well, what could he do if he could?

The answer to this question was given by artificial intelligence developer Mckay Wrigley. Wrigley, using iPhone and MacBook, thanks to the software he wrote ChatGPT given an ‘eye’. ChatGPT also made suggestions based on surrounding objects.

Video in which ChatGPT has the eyes:

All objects around Wrigley, as well as the food and drinks in the refrigerator, are recognized by a signature artificial intelligence. This data is then presented to ChatGPT. ChatGPT, with a question first learns which objects are nearbythen answers another question about these objects.

With this method, Wrigley ChatGPT shows and learns the objects in the fridge. It then asks ChatGPT to provide a recipe that matches the contents in the fridge. ChatGPT, after a short search on the internet explains the correct recipe.

Voice conversation in the video is obviously not something that ChatGPT can do. Wrigley used OpenAI for direct text-to-audio conversion. From Whisper AI uses. All the artificial intelligence he uses and the uses are as follows:

• GPT-4: The language model that ChatGPT creates
• YoloV8: Artificial intelligence that identifies objects visible to the camera
• To whisper: Convert text to audio
• Google Custom Search Engine: Tool that allows ChatGPT to search the web

Wrigley runs these artificial intelligences along with the codes he wrote in Python, and such a result is obtained. Wrigley is also in favor of the augmented reality glasses Apple is preparing to launch. willing to develop tools say.

In other words, the video above is a concrete presentation of the potential of augmented reality glasses that we already know.