Microsoft has released a public test site for their CaptionBot
, an artificial intelligence which attempts to analyze images uploaded by you and then provide a coherent English language description of them. For example, when I uploaded this photo of my dog...
...CaptionBot responded: "I think it's a dog laying on the ground." Not bad. Can't really expect a disconnected intelligence born in cyberspace to understand the distinction between a deck and the ground with such meager visual cues. A few more test images yielded similarly impressive results, sometimes with minor errors of interpretation.
Then I uploaded this photo and the response is pure gold:
"I think it's a person holding a sign and he seems 😐"