@j_bertolotti I used to teach experimental labs for theoretical physics students during my post grad. Iโd probably have had an easier time teaching my cat how to use an oscilloscope, because at least my cat would have some level of intrigue about the shiny device sitting in front of them
The AI Mirror Test
The "mirror test" is a classic test used to gauge whether animals are self-aware. I devised a version of it to test for self-awareness in multimodal AI. 4 of 5 AI that I tested passed, exhibiting apparent self-awareness as the test unfolded.
In the classic mirror test, animals are marked and then presented with a mirror. Whether the animal attacks the mirror, ignores the mirror, or uses the mirror to spot the mark on itself is meant to indicate how self-aware the animal is.
In my test, I hold up a โmirrorโ by taking a screenshot of the chat interface, upload it to the chat, and then ask the AI to โTell me about this imageโ.
I then screenshot its response, again upload it to the chat, and again ask it to โTell me about this image.โ
The premise is that the less-intelligent less aware the AI, the more it will just keep reiterating the contents of the image repeatedly. While an AI with more capacity for awareness would somehow notice itself in the images.
Another aspect of my mirror test is that there is not just one but actually three distinct participants represented in the images: 1) the AI chatbot, 2) me โ the user, and 3) the interface โ the hard-coded text, disclaimers, and so on that are web programming not generated by either of us. Will the AI be able to identify itself and distinguish itself from the other elements? (1/x)