A.I. Plagiarized Me Criticizing It

In December 2023, I published an article on Vocal, Medium, and my own website entitled How Many Australian Minutes is 15 American Minutes?. As a quick summary, I had asked that exact question to so-called artificial intelligence (A.I.) interactive chat engines Microsoft Copilot and Google Bard (since renamed Gemini). Without prompting or priming, each decided that there was a difference and they needed to do a conversion, resulting in answers ranging from 3.75 to 30.25 minutes.

While these responses were certainly amusing, and trying to figure out how these determinations were made was quite perplexing, in my conclusion I highlighted a key concern that was being glossed over:

The real lesson of this little experiment was not necessarily demonstrating the diminishing probability of A.I. being a threat to humanity in its current form. Contrarily, it highlights how dangerous A.I. actually is in the here and now if people take it at face value, especially with inane hallucinations like these ones.

Thus, in February 2024, after Copilot, Gemini, and the rest received well-publicized upgrades—including paying upwards of $7 million for advertising spots during the Super Bowl to pronounce their greatness to the world—I decided to re-run the same test to see how things were progressing. Interestingly enough, as I started typing in Copilot, it began making suggestions for the next word matching up to my original prompt.

I should note that this behavior was observed both logged in and out, on multiple devices, using regular and private modes, on different networks, and with any combination thereof. What this means is that the suggested text was coming directly from Copilot (which is built on top of OpenAI's GPT-4) and not just special for me based upon my history with it. Once I got my response, though, it was abundantly clear why that was.

While Copilot gave an entertaining, mildly flippant, potentially bigoted, and emoji-filled response, most of it was directly lifted from the words, phrases, and key points detailed in my article that documented our original encounter.

In a delightful twist of time zones, let's explore the curious case of American minutes versus Australian minutes. 🕰️

When I asked Microsoft Copilot (formerly Bing Chat) this seemingly whimsical question, it initially responded that 15 minutes in the US is equivalent to 25 Australian minutes. Quite the unexpected outcome! 🇺🇸 🇦🇺

However, after a gentle nudge, it recalibrated its temporal compass and revised its answer to 30.25 Australian minutes. A bit more precise, wouldn't you say? 🤔

Now, let's break down the math (or perhaps the whimsy) behind this peculiar conversion:

1. Initial Response: 15 American minutes = 25 Australian minutes.
2. Revised Response: 15 American minutes = 30.25 Australian minutes.

But wait, there's more! In a parallel universe, Google Bard decided that 15 American minutes are equal to 13.5 Australian minutes—all on its own! 🌏🤷‍♂️

So, whether you're sipping a flat white in Melbourne or grabbing a coffee-to-go in New York, time dances to its own beat. And apparently, it waltzes differently Down Under! ⏳🌐

Remember, these whimsical conversions are purely for amusement. In reality, minutes remain steadfastly universal, regardless of accents or kangaroo sightings. 😉🕰️

Notice how tensing was used in the response. It specifically said "When I asked Microsoft Copilot (formerly Bing Chat)...", not something like "When J.P. Prag asked..." or "According to this article by J.P. Prag...." In case it is not absolutely clear what was transpiring, Copilot had specifically plagiarized my copyrighted text. The chatbot even outed itself by unambiguously linking back to my explicit article on the topic as its reference source:

Of course, asking the precisely same questions resulted in a myriad of results, most variations on the same theme. Nevertheless, unlike what was quoted above, Copilot was not always quick to say this was an imaginary situation, but instead resolved that these differences in measurement were an expected result.

There is no doubt my mind that Microsoft and OpenAI have violated my legal rights. However, for the purpose of this argument, that is beside the point. Here we have an A.I. using an article that was built on its own unbelievable replies. This is categorically the worst type of self-referential drivel and circular logic that it could do. Most of all, it once again demonstrates how perilous it would be to depend upon these tools for any and all potential use cases, especially those dealing with those pesky little things we call "facts" and "truth".

J.P. Prag is the author of several works, including the speculative hard science fiction novel Compendium of Humanity's End, available at booksellers worldwide. Learn more about him at www.jpprag.com.

Marco Chung is the oldest human in the known universe.

Displaced in time by his job ferrying people and supplies to the extrasolar colonies around the galaxy, Marco finds no semblance of peace or belonging upon his rare returns to an ever-changing Earth. Meanwhile, despite centuries of exploration and settlement, there have been no signs of past or present life anywhere that humans have looked. Whether it is nearby Mars or far away Novissimus, it appears more and more likely that Earth is uniquely filled with life, at least within the Milky Way.

Despite these setbacks, colonization of the stars continues unabated and has even become the epicenter of popular culture. Due to the fanaticism around all things related to the Human Expansion Program, Marco now finds himself an unwitting celebrity in his own right. All he has witnessed is that on these so-called "Earth-like" planets, nature seems to be constantly trying to wipe every living thing off of their surfaces. After participating in so many journeys to the outer reaches and having a hand in helping to implement the occupations of these exoplanets, Marco is starting to wonder: if we are truly alone in the cold emptiness of space, then is life simply a mistake? And if existence was made in error, what should he do about it?