ChatGPT, developed by OpenAI, has received a significant upgrade in its computer vision capabilities.
The AI now has multimodal abilities and can analyze and understand images.
The latest reasoning models, o3 and o4-mini, can manipulate images to extract relevant information and make sense of blurry details, resembling computer vision in movies.
This advancement brings ChatGPT closer to the fictional enhancement of images seen in movies, though still far from real-life possibilities.