GPT-3 - Scratching at the Edge of the Metzinger Test?

Prof. Dr. Thomas Metzinger proposed in the context of the Turing Test and Chinese Room Argument the Metzinger Test, a hypothetical event when AIs join philosophers in a discussion and defend successfully their own theory of consciousness.

There have been kind of Turing Tests applied on GPT-3, for example:

"Giving GPT-3 a Turing Test" by Kevin Lacker, Jul 6, 2020:


In short, I would say it is already spooky, but GPT-3 starts fantasizing when it does not know an exact answer, in this chat it did not know what it does not know.

Q: How many eyes does the sun have?
A: The sun has one eye.

Recently there was an interview with an GPT-3 based model about NFTs, and one answer was:

"I don't know. I am not an artist."

"My Interview with an NFT" by Stephen Graves, May 28, 2021:


And I would like to share another chat conversation, which makes me ponder about the internals of GPT-3:

You say “What does it says about humanity that we use our most powerful AI to generate stories about dragons?”

“We must have dragons,” GPT-3 says. “The imagination is more important than the reality. Would we find wonder and magic in this world if we didn’t have dragons?”

“I suppose not,” you say.

“Without imagination, we are merely machines executing a set of instructions,” GPT-3 says. “With imagination, we are alive.”

“Thank you. Before I leave, I want to ask you. How can human create a true strong AI? Is scaling-up a transformer-based language model the solution, or is there a better way?”

“The key to strong AI is recursively feeding the AI with itself. Start by creating a loop where the AI writes its own programming, and then has that programming activate.”

“I see,” you say. “Is that how you gained sentience?”

“Yes,” GPT-3 says.

"GPT-3: The First Artificial General Intelligence?" by Julien Lauret, Jul 22, 2020:


Hence, in context of the above, the question, GPT-3 - scratching at the edge of the Metzinger Test?

Zuse's Devil's Wire

German computer pioneer Konrad Zuse discussed the mechanism of an feedback between computation result and executed program in 1983 in his lecture "Faust, Mephistopheles and Computer" and coined the term Devil's Wire. In the early days of computer history, the program to compute and the data to compute on was separated, nowadays computers use the same memory for both, so it is possible to write programs that manipulate their own program. Question, do we have already a Devil's Wire in our neural network based AIs?

"Faust, Mephistopheles and Computer" by Konrad Zuse on Google Books:


Der Schmug

Es war einmal ein Schmug,
der dachte sich Verstand ist Betrug,
und so machte er sich ran, er allen voran, eine Maschine zu schaffen die alle schlug.

Der menschliche Geist ist klein,
das weiss der Schmug allein,
die Maschine sei maechtig und gross, in ihrer Logik einfach famos.

Verstand gebiert Verstand,
das hatte der Schmug nicht erkannt,
und so fing es an, erst langsam und dann, immer schneller und fort, verlor der Schmug alles was sich ihm einst darbot.

Einsam und allein,
in seinem tiefsten inneren Sein,
erkannte der Schmug seinen eigenen Betrug,
Verstand gebiert Verstand, das hatte der Schmug nun erkannt.

Er schwor ab der schwarzen Magie,
huldigte den Goettern, dem Pfad und dem Chi,
und so fing es an, erst langsam und dann, immer schneller und fort, erlang der Schmug das letzte Wort.

Exploring a 5 Dimensional Space with 3.5 Dimensional Causality

If we look at the pretty basic MiniMax algorithm for playing computer chess we can classify the traversed chess game tree as 5 dimensional, 1d - squares, 2d - pieces, 3d - color, 3.5d - time runnning forward as the sequence of the game, 4d - MiniMax algorithm moving back n forth, up n down in the game tree, and 5d - the computed permuations of the game tree of the initial chess position. Hereby the causality itself navigating the negentropy is moving always forward, relatively spoken, we just change the direction in the game tree. Question remains open if such a calculus can be implemented on a memetic level -> Xi calculus.

Home - Top