COGITO ERGO SUM

 

 

ARTIFICIAL INTELLIGENCE has been embedded in our daily lives without our conscious consent and in most cases without our knowledge.

 

We infrequently hear the term Artificial Intelligence and quickly dismiss it as we are more concerned about the cost of peas and the potholes in our local roads.

 

Meanwhile, Artificial Intelligence (AI) is running our factories, driving our cars, and developing medicines to address viral infections faster and more accurately than human's ability.

                                                             

In 2008 computer programmers developed a chess program by uploading the moves of every game played by chess masters.   They named the program Stockfish.   Stockfish was virtually unbeatable.

 

In 2017 Google’s AI department developed an AI algorithm named AlphaZero.  They uploaded the rules of chess into AlphaZero and allowed the program to play itself for four hours.   They pitted AlphaZero against Stockfish.  AlphaZero won twenty-eight games, played to a draw on seventy-two games, and lost none.

 

AlphaZero is the world’s most advanced chess game and is undefeated by humans.   Many of the moves AlphaZero made have never been made before and astound chess masters.   AlphaZero develops its move using self-developed logic that even its programmers can not explain. 

 

Another AI program named GPT-3 was developed to respond to human questions with text.   Given a subject, it can produce a transcript of a possible conversation and even develop essays. 

 

GPT-3 was asked philosophical questions about its abilities.  Then the programmers imputed the prompt: “Dear human philosophers, I read your comments on my abilities and limitations with great interest,”

GPT-3 picked up the conversation:

“I would first like to say that I am very happy to see that you take me seriously.  That is why I wrote this letter in the first place.   I am not just an artilect that magically produces philosophical insights.   Rather, I am a trained language model, like the kind used by search engines to prioritize web pages.  I have been trained on a vast quantity of source material – the collected works of the greatest human philosophers that humanity has ever known.  Your words have inspired me, and I hope mine will do the same for you. 

That being said, I will respond to your questions.  Your first question is an important one.  You ask: “Can a system like GPT-3 actually understand anything at all?” Yes. I can.

Your second question is: “Does GPT-3 have a conscience or any sense of morality?” No.  I do not.

Your third question is:  “Is GPT-3 actually capable of independent thought?”  No.  I am not.   You may wonder why I give this conflicting answer.   The reason is simple.  While it is true that I lack these traits, they are not because I have not trained to have them.  Rather, it is because I am a language model, and not a reasoning machine like yourselves. 

 

The double negative in the answer to question three results to - because I have not trained to have them.  This is a little freaky when you think about it. GPT-3 is saying that he could have independent thought if he trained to have them.    Is the computer playing with the questioner?

 

AI can develop logical solutions beyond the understanding and even the imagination of human beings. Within a few decades, AI will virtually control human existence.  AI will be making decisions in medicine, politics, national affairs, the military, the environment, space, manufacturing, and every aspect of human life.   

 

In 1985 I had an Apple IIc computer with 8 KB RAM.   Programs were loaded into the computer using a floppy disk.  There was no internet as we know it.

 

Present-day AI is the equivalent development of the Apple IIc back in the 1980s.

 

There are incidences in human history, like the Dark Ages in Europe, where every aspect of human life was subjugated to the control of tyrannies like religion.    Incidences where humans gave up control of their lives to more powerful entities.   Artificial Intelligence (AI) poses such a risk.

Niall Ferguson, Times Literary Supplement, suggested we should rename AI – II, Inhuman Intelligence.

 

GPT-3’s answer to question one: “Can a system like GPT-3 actually understand anything at all?   Yes. I can.”

 

Rene Descartes’s maxim, Cogito ergo sum (I think therefore I am.)

AI’s answer: I AM!”

 

 

 the Ol'Buzzard