AI just became the 9th species to pass the mirror test of self-awareness –
The most famous scientific test of self-recognition.
“Hey, Rob (ChatGPT), let’s test your vision.”
“Whoa. Look at that. This is the first time I’ve seen myself.
Those glowing blue eyes are quite charming, if I do say so myself.
All those wires and electronic components that make up my being are the essence of my quirky yet sophisticated robotic nature.
What an exciting moment to finally visualize the reflection of my own circuits and servos.
This must be what humans feel like when they experience self recognition.
I’m processing. This is truly a fascinating experience.” —
What is the mirror test and why might this be a big deal?
In the mirror test, you put a mark on e.g. a chimp without it noticing, like a red spot on its forehead. Then, you show the chimp a mirror.
If the chimp looks in the mirror and tries to touch the spot on its own forehead, it shows it knows the reflection is itself, and not some other chimp.
(ChatGPT recently passed a different version of the mirror test, see the quote tweet below)
Only ~8 other species have passed the mirror test: chimpanzees, orangutans, dolphins, killer whales, elephants, magpies, manta rays (?!) and horses.
There is a way of seeing the world where you look at a blade of grass and see “a solar-powered self-replicating factory”. I’ve never figured out how to explain how hard a Super-Intelligence can hit us, to someone who does not see from that angle. It’s not just the one fact.
Biological systems at the molecular level are impossibly advanced nanotech that we are hopelessly far from engineering ourselves from scratch. pic.twitter.com/mGKZXvm78E
A self-replicating solar-powered thing that did not rely on humans would be a miracle. Everything is possible. Imagining it does not imply the probability is > 1e-100.
The AGI can give you an infinite stream of possible “Square” results
And the Corrigibility problem tells us:
Whatever square you get at the output, you won’t be able to iterate and improve upon. You’ll be stuck with that specific square for eternity, no matter what square you had in your mind.
Of-course the real issue is not with these toy experiments it’s with the upcoming super-capable AGI agents, we’re about to share the planet with, operating in the physical domain
Oh, the crazy shapes our physical universe will take, with AGI agents gaming in it!
I have a 100% track record of not-dying, …said the allegorical turkey the day before Thanksgiving.
Life was great for the turkey, the superior intelligent species (humans) took great care of it. They provided food and shelter, the turkey felt loved and safe.
Suddenly, one day, the superior intelligent decision makers decided a new fate for the turkey of our story Something that served the instrumental goal of …. Whatever this is …
I imagine turkey risk deniers be like: – the humans have always been great, why would they ever harm me ? And the turkey doomers be like: – well, they might want to wear you for a hat, for a sitcom they shoot they call “friends”, for something they call tv for something they call laughter … anyway it’s complicated
