Meta shares AI model that can detect objects without prior training

  • AI typically needs to be trained on existing material to detect objects.
  • Meta has a “Segment Anything” AI model that can detect objects in pictures and videos without prior training.
  • Objects can be selected by clicking them or using free-form text prompts.
  • For example, users can type the word “cat” and the AI will highlight all cats in the photo.


Sign Up for nextbigwhat newsletter

The smartest newsletter, partly written by AI.

Download, the short news app for busy professionals