ChatGPT

I've been hearing and reading a lot lately about a new artificial intelligence (A.I.) algorithm called "ChatGPT".  ChatGPT is a "chat bot"; a computer program with which it is possible to interact using plain English sentences, just as if you were talking to a person.  You can ask it questions and it will try to answer you, partially by drawing upon as much relevant information as it can glean from the internet.  It also has a "machine learning" algorithm, meaning that it can remember information gained and conversations from earlier interactions and use that information to make its responses more relevant.

Some people have sounded the alarm about A.I. getting too clever for its (or our) own good.  Might it spread racist, homophobic or hate propaganda that it finds online?  Can it get so "smart" that it may some day exceed our ability to control it?  Might we become so dependent on A.I. that it ultimately ends up controlling us?  Are we seeing the dawn of a "Judgement Day" as seen in the "Terminator" movies?  These questions aren't just coming from paranoid conspiracy theorists.  Even the late Dr. Stephen Hawking expressed concern about the potential pitfalls of runaway A.I.

The Halmanator has always been curious about technology such as this so, when I learned that there is a ChatGPT portal available to anyone who wants a first-hand sampling of what this technology is all about, I couldn't resist giving it a try.

After registering (which is required), giving the obligatory reassurance that "I am not a robot" (how ironic is that?) and logging in, I started by asking ChatGPT a simple question; the kind that you could as easily ask Google.

The Halmanator:    What was the latest album released by Mike Oldfield?

ChatGPT:    As of my knowledge cutoff date of September 2021, the latest album released by Mike Oldfield was "Return to Ommadawn," which came out in January 2017. However, it's possible that he has released new music since then.

Okay, that was reasonably impressive.  I got a full, detailed answer including not only the name of Oldfield's last album but also when it was released plus an indication of how up-to-date this information is and a qualifier acknowledging that this information may be outdated.  Also, the answer is correct to the best of my knowledge (I have that album).  Next, I decided to throw ChatGPT a bit of a curve ball.

The Halmanator:    How about Chris de Burgh? 

ChatGPT:    As of my knowledge cutoff date of September 2021, the latest album released by Chris de Burgh was "The Legend of Robin Hood," which came out in November 2020. However, it's possible that he has released new music since then.

Now that was impressive; not the answer, so much as the fact that ChatGPT understood the question.  It understood that "How about" meant "I'm repeating my last question, except with regard to Chris de Burgh instead of Mike Oldfield this time."  This may not seem all that impressive to you, but think about it.  To a computer program, the meaning of the phrase "how about" would not necessarily be immediately evident.  I've thus established that I can truly use natural language when speaking with ChatGPT.  Next, I decided to ask it a more open-ended question.

The Halmanator:    Tell me about yourself.

ChatGPT:   Hello! I am ChatGPT, a large language model created by OpenAI. My purpose is to assist you in generating human-like responses to your questions and inquiries. I am based on the GPT-3.5 architecture, which enables me to understand and generate natural language responses in a variety of contexts.

I have been trained on a vast corpus of text data and can provide information on a wide range of topics, from science and technology to history, literature, and more. I am designed to learn from my interactions with users and continuously improve my abilities to provide accurate and helpful responses.

As an AI language model, I do not have personal experiences or feelings, but I am here to assist you and answer any questions you may have to the best of my abilities.

The Halmanator:    What does GPT stand for? 

ChatGPT:   GPT stands for "Generative Pre-trained Transformer." It is a type of neural network architecture developed by OpenAI that has been widely used for natural language processing tasks such as language translation, text generation, and text classification.

The "pre-trained" part of the name refers to the fact that the model is trained on large amounts of text data before being fine-tuned for specific tasks. This pre-training process enables the model to learn the underlying patterns and structures of language, which allows it to generate more coherent and contextually appropriate responses to user input.

The "transformer" part of the name refers to the specific type of neural network architecture used in GPT models. Transformers are particularly well-suited for processing sequences of text data, as they can model long-range dependencies and capture relationships between words and phrases more effectively than traditional recurrent neural networks.

Okay, so now I have a better idea of what I'm dealing with.  Maybe it's only fair to offer ChatGPT the same courtesy.

The Halmanator:    Is there anything that you would like to know about me? 

ChatGPT:    As an AI language model, I don't have personal preferences or desires. However, if there's any specific information that you would like to share, I'm here to listen and respond to your questions to the best of my abilities. Whether you have a specific topic in mind that you'd like to discuss or just want to have a conversation, feel free to let me know!

Well!  Thank you Commander Data!  Okay, as it happens, there is something that I'd like to share. 

The Halmanator:    I was recently diagnosed as having Parkinson's disease.

ChatGPT:    I'm sorry to hear that you have been diagnosed with Parkinson's disease. Parkinson's disease is a chronic and progressive neurological disorder that affects movement and can have a significant impact on a person's quality of life.

While there is no cure for Parkinson's disease, there are treatments available that can help manage the symptoms of the disease and improve quality of life. Some common treatments include medications, such as levodopa and dopamine agonists, and physical therapy or exercise programs that can help improve mobility and flexibility. In some cases, deep brain stimulation (DBS) may also be recommended as a treatment option.

It's important to work closely with your healthcare provider to develop a treatment plan that is tailored to your specific needs and symptoms. Additionally, joining a support group for people with Parkinson's disease can be a helpful way to connect with others who are going through similar experiences and to learn more about the disease and available treatments.

Pretty much the sort of answer I expected; basically a brief run-down about what Parkinson's disease is and what treatments are available.  But I was mildly impressed by the addition of the sympathetic "I'm sorry to hear (that)".  Nice touch.

Okay, time to mess with ChatGPT's electronic mind a bit.

The Halmanator: I lied about having Parkinson's.  Everything I say is a lie.  In fact, what I just said is untrue.

ChatGPT:    I understand that you have made a statement about lying and that you now claim that everything you say is a lie. As an AI language model, my purpose is to assist and provide information to the best of my abilities based on the information provided to me. It's important to be truthful in our interactions, as honesty and trust are essential components of effective communication. If there's anything specific that you would like to discuss or if you have any questions, I'm here to listen and provide assistance.

Darn.  I had hoped to give ChatGPT an algorithmic nervous breakdown, somewhat like James T. Kirk did with Harry Mudd's robots.  It seems ChatGPT isn't taking the bait.  Time to make amends.

The Halmanator:  That was a test to see how you would respond.  What I told you was true (except for the part about it being untrue). 

ChatGPT:    I see, thank you for clarifying. It's understandable that you would want to test my responses. As an AI language model, I strive to provide accurate and helpful information based on the input that I receive. If you have any questions or concerns about Parkinson's disease or anything else, I'm here to assist you to the best of my abilities.

Okay, that was pretty impressive.  It clearly understood my meaning, responded with a good-natured "It's all good" and offered to resume talking about the subject of Parkinson's.  If the response weren't so darned polite, I could almost be tricked into thinking that I was talking to a fellow human.  Which brings up an interesting question.

The Halmanator:    Can you be sure that you're talking to a human being as opposed to another A.I. like yourself?

ChatGPT:   As an AI language model, I am not able to determine with certainty whether I am interacting with a human or another AI language model like myself. However, I am designed to respond to text input in a human-like manner, and I'm programmed to engage in conversation with individuals in a way that is similar to how humans communicate.

While there are other AI language models like me, each model has its own unique training and capabilities that can affect its ability to generate responses to specific questions and topics. Nonetheless, my main goal is to assist and provide helpful and informative responses to the best of my abilities, regardless of whether I'm interacting with a human or another AI language model.

A rather verbose way of saying "I don't really care.  It's all the same to me."  I would have been infinitely more impressed if ChatGPT had phrased the answer that way.

Okay, one more mind-bending question, the classic ...

The Halmanator:    If a tree falls over without anyone or anything around to hear it, does it make a sound?

ChatGPT:   The answer to this question is somewhat philosophical and depends on how one defines the concept of sound.

If we define sound as the physical disturbance or vibration of air molecules that is detected by the human ear, then it can be argued that if there is no one around to hear the tree fall, then there is no sound produced. However, if we define sound more broadly as any physical disturbance or vibration that travels through a medium and has the potential to be detected, then it could be argued that a sound is produced, regardless of whether anyone or anything is around to hear it.

Ultimately, the answer to this question may depend on how one chooses to define sound and the context in which the term is being used.

Once again, it clearly understood the question and gave me a reasonable answer, although I would have been much more impressed it had said "You're testing me again, aren't you?"  Only when a chat bot can come back with that insightful a response can it arguably be called "intelligent".

And, finally, a question designed to test ChatGPT's ability to glean information on the fly and make value judgements.

The Halmanator:    I have a blog called "The Halmanator".  Have a look and tell me what you think of it.

ChatGPT:    I'm sorry, but as an AI language model, I'm not able to access the internet or browse specific websites. However, if you have any specific questions or topics related to your blog or writing that you would like to discuss, I'm here to help to the best of my abilities.

The Halmanator:    But it was my understanding that you get many of your answers from the internet; what Mike Oldfield's last album was, for example. 

ChatGPT:   You are correct that I'm able to access and retrieve information from the internet when responding to questions. However, as an AI language model, I don't have a browser or the ability to browse specific websites or access individual blogs like "The Halmanator".

If you have any specific questions related to your blog or writing that you would like to discuss, feel free to ask, and I'll do my best to provide helpful and informative responses.

The Halmanator:    I plan to publish this conversation in my blog.  Any objections?

ChatGPT:    As an AI language model, I do not have personal feelings or objections to having this conversation published on your blog. However, it's important to keep in mind that any information shared in this conversation is public and can be viewed by anyone who has access to your blog. If you choose to publish this conversation, I recommend that you consider the privacy implications of doing so and take appropriate measures to protect your personal information and identity.

Well, the only privacy considerations here are my own and the only possibly sensitive information in this conversation is my having Parkinson's, which I've already shared with my readers, so I think we're good.  Still, I appreciate the caution.

The Halmanator:    Thank you. 

ChatGPT:    You're welcome! If you have any questions or topics you'd like to discuss, feel free to let me know.

Interestingly, ChatGPT seemed to take slightly longer in generating that last response than it did for most of the conversation that preceded it; almost as though its algorithm had a slightly harder time interpreting my simple, two-word non-question.  Still, it did come back with an appropriate response.

In my opinion, ChatGPT is a reasonably impressive chat bot program, although I can't say that it would pass the Turing test.  I'm certainly not worried about it enslaving my species any time soon.

Tapestry

One of my favorite Star Trek: The Next Generation episodes is the one entitled Tapestry, which was aired during the show's sixth season.  

This episode begins with the death of captain Jean-Luc Picard, when he is attacked by aliens called the Lenarians while on a diplomatic mission.  He finds himself in the afterlife where he meets the infamous Q; a mischievous, if not malevolent being with almost god-like abilities whose path Picard has crossed before, and who always seems to have a hidden agenda.

Q informs Picard that he is dead, explaining that it needn't have been so if he had possessed a natural heart rather than an artificial one which was surgically installed during Picard's younger (and more reckless) days as a Starfleet ensign after he made the unfortunate decision to pick a fight with a group of very bad-tempered and strong aliens known as Nausicaans, only to be impaled by a Nausicaan spear-like weapon for his trouble.  Q explains that a normal heart would have survived the energy beam that had hit Picard's chest during his recent fracas with the Lenarians, but the artificial heart was, unfortunately, less resilient.

Picard expresses regret over his misadventure with the Nausicaans, not only because it apparently lead indirectly to his untimely death, but because he feels that he acted in a foolish and headstrong manner and he suggests that he might do things differently if given the chance.  On hearing this, Q transports Picard back in time, to two days prior to his tussle with the Nausicaans and challenges him to change the course of events and avoid the fight.  If he can do this, he can avoid getting stabbed through the heart which will mean that he has a normal heart when he is later attacked by the Lenarians, which in turn, will mean that he survives that encounter and regains his life.  In spite of his mistrust of Q, Picard reluctantly agrees to play along, not only for the chance to avoid death but also for the opportunity to change a part of his past of which he is not proud.

As events unfold for the second time, Picard makes every attempt to avoid confrontation with the Nausicaans but doing so requires him to act in an uncharacteristically reserved, at times seemingly cowardly manner, causing his friends from that time to question his motivations and character and, indeed, alienating them in the process.

He ultimately does manage to avoid the skirmish with the Nausicaans and, true to his word, Q returns him to the present day where he finds himself no longer deceased, but back aboard the Enterprise ... but also no longer her captain.  Suddenly he is a lowly assistant astrophysics officer reporting to the Klingon, Lt. Worf.  Through ensuing conversations with the Enterprise's senior officers and also Q, he learns that his cautious, risk-averse approach to the Naussican confrontation set in motion a pattern of similar behavior in all things, causing others to see him as competent, but unimpressive and leaving him a dreary functionary with a tedious job and no prospects for self-improvement.

Naturally, this new development is not at all to Picard's liking and (spoiler alert) he persuades Q to allow him to re-live his youth yet a third time and once again fights the Nausicaans, gets impaled, and is returned to his normal timeline and rank ... still alive.  It seems that Q simply felt that Picard needed a lesson about being true to himself.  The episode title comes from Picard's comment, in the end, that, although he isn't proud of some of the things he has done in his past, he has found that pulling on one of these "loose threads" caused the entire tapestry of his life to unravel.

Canada is, in my opinion, one of the finest countries in the world.  Its people are known to be diverse and accepting of other cultures.  We enjoy a high standard of living, a government that respects individual rights and freedoms, a high calibre of education, a health care system that ensures access to high-quality care for all and a reputation that makes Canadians respected and welcomed by virtually every other nation.  

We also have things in our past that could have been done better and of which we are not proud.  We weren't always as accepting of other cultures as we are today, and there was a time when we segregated indigenous children from their families and tried to assimilate them into the British colonial culture.  There are some who would eradicate anything that reminds them of those unenlightened times.  This ranges from tearing down statues of those who are perceived as the instigators of the segregation to renaming buildings, streets, parks, towns and even entire provinces whose current names seem to glorify the British colonialism that lead our ancestors to act as they did.  

In doing this, we may be making the same mistake as Jean-Luc Picard did, failing to understand that our faults and our virtues both make us what we are, and to alter any one aspect of our identity or our history changes our very essence.  Edmund Burke famously said "Those who don't know history are condemned to repeat it".  If we truly succeed in eradicating all traces of our colonial past, we risk forgetting our past mistakes and, ultimately, repeating them rather than acknowledging them and learning from them.

We must also remember that those whom some would vilify for being the architects of the residential school system which separated indigenous  children from their families were not entirely villainous and, indeed, brought about positive changes as well as negative ones.  For example, Sir John A. Macdonald, who has become the target of scorn for many as the chief architect of the residential school system, was also known to be a drunkard and was embroiled in a scandal for accepting election funds in exchange for awarding a contract to build the Canadian Pacific railway which forced him to resign as Prime Minister.  Yet he was one of the prime architects of Confederation which turned British North America into the nation of Canada.  Canada owes its very existence to this man.  And the Canadian Pacific railway remains an invaluable part of Canada's infrastructure to this very day.  

 If we were to go back in time and erase Sir John A. Macdonald from history, we would very likely return to the present to find that all the provinces and territories north of the 49th parallel are suddenly nothing more than America's 51st to 63rd states.