Und Scott Alexander sieht in der K.I. einen ersten (kleinen) Schritt in Richtung GAI (General Artificial Intelligence, deutsch Starke Künstliche Intelligenz), die sich spielerisch ein eigenes Modell der Welt zusammenpuzzelt, ähnlich wie es Kinder tun –> Do Neural Networks dream of electric Hobbits? und GPT-2 as step towards general intelligence.
Janelle Shane asks GPT-2 its ten favorite animals:
Prompt: My 10 favorite animals are: 1.
My ten favorite animals are:
1. Zebras with a white scar on the back
2. Insiduous spiders and octopus
3. Frog with large leaves, hopefully black
4. Cockatiel with scales
5. Razorbill with wings hanging about 4 inches from one’s face and a heart tattoo on a frog
3. Cockatric interlocking tetrabods that can be blind, cut, and eaten raw:
4. Black and white desert crocodiles living in sunlight
5. Zebra and many other pea bugs
Forget the particular animals for now (don’t worry, the razorbill with wings hanging about 4 inches from one’s face will be back in your nightmares). Notice the way it numbers its list: 1, 2, 3, 4, 5, 3, 4, 5. Last week the two-year-old child who lives next to me counted 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 8, 9, 7, 8, 9, 7, 8, 9 (his mother warns this is an inexact transcription). GPT-2 is instantiated on giant supercomputers; it’s a safe bet they could calculate the square root of infinity in a picosecond. But it counts more or less the same way as a two-year old. GPT-2 isn’t doing math. It’s doing the ridiculous “create a universe from first principles and let it do the math” thing that humans do in their heads. The fact that it counts so badly suggests it’s counting human-style, which makes it amazing that it can count at all. […]
A brain running at 5% capacity is about as good as the best AI that the brightest geniuses working in the best-equipped laboratories in the greatest country in the world are able to produce in 2019. But:
We believe this project is the first step in the direction of developing large NLP systems without task-specific training data. That is, we are developing a machine language system in the generative style with no explicit rules for producing text. We hope for future collaborations between computer scientists, linguists, and machine learning researchers.
A boring sentiment, except for the source: the AI wrote that when asked to describe itself. We live in interesting times.