feature article
Subscribe Now

Gruesome Gambols Gripping Generative AI (Part 2)

I’m not having a good day. “Why so?” You ask. Well, thank you so much for caring. I have a sad tale to tell—one that will doubtless bring a little tear to your eye. I stand before you a broken man, hanging my head in shame, with my credentials as an engineer hanging in tatters.

Since we have so much of an artificial intelligence (AI) nature to talk about, I’ll cut a long story short, which is opposite to the way I usually like to do things. Earlier this week, I celebrated the 33rd anniversary of my 33rd birthday. To keep me fit and healthy, my wife (Gina the Gorgeous) gave me a bicycle. It arrived in a flat-pack box (the bicycle equivalent of a chest of drawers from Ikea).

I assembled most of the bike in short order, but it appeared they had sent the wrong front wheel because there was no obvious way for the hardware on the wheel’s hub to attach to the front fork. “Oh dear,” I thought (or words to that effect). Eventually, I swallowed my pride and took the beast to a local bike store. The manager rooted around in the box of bits and pieces that came with the bike, pulled out a doodad whose purpose I’d pondered in passing, waved his hands around in a blur like a street magician performing a card trick, and—with an overly theatrical flourish (I thought)—presented the fully assembled bike in all its glory. I thanked him profusely and headed home.

This morning, Gina and I intended to take a quick spin before I headed off to my office. Before we set off, however, I foolishly decided to tweak the angle and height of the seat. Unfortunately, I loosened one too many things at the same time, with the result that the rod holding the seat promptly fell into the frame while the seat itself fell on my foot (“Oh, my toe bone,” as Deputy Dawg might say). Somehow, the rod managed to jam itself in the frame in such a way that I could not extract it (yes, of course I tried turning everything upside down and hitting it with a mallet; my parents didn’t send me to university for nothing). I just visited the bike shop again to present them with my machine and its newly detached seat. I’m sure they were straining not to smirk. As I said, I’m not having a good day.

But we digress… In Part 1 of this mini-series, we introduced the concept of generative AI, which refers to an AI capable of generating text, images, or other media in response to prompts. There are many of these tools out there, but the one on everyone’s lips is, of course, ChatGPT, which is an AI chatbot developed by OpenAI.

This image of a robot working on a computer was created by a generative AI (Source: Paxabay)

When we consider that ChatGPT was made available in November 2022, it’s amazing how many inroads it’s made into our collective consciousness. Almost immediately, I started hearing from friends who were performing experiments with this little scamp. For example, my chum Joe Farr in the UK asked ChatGPT if it was possible to write a BASIC Interpreter in C#, and he was amazed to see one being written before his very eyes. He says there were a few bugs, like using some of BASIC’s keywords as variable names, but that it was a good attempt overall (see also my column on Metabob, which is a generative AI that identifies and addresses bugs in code created by other generative AI tools, like Copilot, which is a cloud-based generative AI developed by GitHub and OpenAI).

Similarly, my friend Rick Curl emailed me to say that he had been tinkering with ChatGPT. As one experiment, he asked it to, “Write an article about semiconductor technology in the style of Max Maxfield,” and ChatGPT came up with the following:

Semiconductor Technology: A Thrilling Journey into the World of Microelectronics

Hello, my dear fellow electronics enthusiasts! I’m Max Maxfield, your friendly neighborhood electronics guru, and I’m here today to take you on an exciting journey into the world of semiconductor technology.

As you may know, semiconductors are materials that have electrical conductivity between that of a conductor and an insulator. These materials are essential in the world of microelectronics and have changed the way we live, work, and communicate. 

The first semiconductor, Germanium, was discovered in 1886, and it wasn’t until 1947 that Bell Labs invented the first transistor, a device that would later revolutionize the electronics industry. The transistor was the cornerstone of the digital age and paved the way for the development of integrated circuits (ICs), which are the tiny chips that power all of our modern electronic devices.

One of the key benefits of semiconductors is their ability to be “doped” with impurities to create p-type and n-type semiconductors. By carefully controlling the doping process, engineers can create junctions between p-type and n-type semiconductors that allow for the flow of electrical current in only one direction. This is the foundation of the bipolar junction transistor (BJT) and the field-effect transistor (FET), two of the most important components in modern electronics. 

In recent years, the semiconductor industry has been undergoing a transformation, with the rise of the Internet of Things (IoT) and the growing demand for more powerful and energy-efficient electronics. This has led to the development of new materials, such as silicon-germanium (SiGe) and gallium arsenide (GaAs), which offer higher performance and lower power consumption compared to traditional silicon-based devices. 

Another exciting development in semiconductor technology is the move towards three-dimensional (3D) integration. By stacking multiple layers of transistors and other components on top of each other, engineers can create devices that are smaller, faster, and more power-efficient than traditional two-dimensional (2D) designs. This is especially important for applications in areas like mobile computing, where the size and power consumption of electronics are critical factors. 

In conclusion, the world of semiconductor technology is a constantly evolving landscape, full of exciting new developments and breakthroughs. Whether you’re an electronics hobbyist, an engineer, or just someone who loves gadgets and gizmos, there’s never been a better time to be part of this thrilling journey. So, join me, my friends, and let’s explore the wonders of semiconductor technology together!

That’s all for now, folks. I hope you enjoyed this thrilling ride through the world of semiconductor technology. Until next time, keep those circuits humming! Yours in electrons, Max Maxfield

Rick was kind enough to say, “While the article was interesting, I certainly would not say it was written by you!” It was unfortunate that he felt compelled to close by saying, “So, no need to worry……YET!”

I’ve been gathering myriad generative AI-related nuggets of knowledge and tidbits of trivia to share with you, but I’m still trying to wrap my brain around all of the thought-provoking implications, so we will leave the in-depth philosophizing until my next (and final) entry in this troika of columns.

For the moment, let me leave the following items for you to peruse and ponder. Let’s start with the fact that, in January 2023, the Intelligent website published a report saying “30% of college students have used ChatGPT on written homework” (remember this was only three months after ChatGPT was first presented to the world).

“Ah ha,” you say, “the answer is to get the students to write their reports by hand.” There are two flaws in this cunning plan. The first is that the students could simply rewrite the machine-readable report generated by ChatGPT. The second is that a clever rascal called Devadeth has created a homework machine that generates text based on the user’s own handwriting.

 

You can almost feel sorry for the Professor who flunked all his students because he asked ChatGPT if they had cheated on their final assignments and ChatGPT claimed it had written their papers for them. It turned out that ChatGPT was lying. Who would have “thunk”?

Quite apart from the moral and ethical issues associated with using a generative AI to create some work—be it textual, graphical, or in some other media—and then claiming that work as one’s own, what are the legal ramifications? Well, one person we could ask is Steven Schwartz of Levidow, Levidow & Oberman. As we read on Reuters (see A lawyer used ChatGPT to cite bogus cases. What are the ethics?), this is a man who is uniquely qualified in this area because he asked ChatGPT for help writing a brief regarding a personal injury case for one of his clients. Silly Stephen asked ChatGPT to cite previous court decisions that would back-up his (well, their) case, and ChatGPT did as requested. Unfortunately, rather than laboriously tracking down real court cases in the style of Jack McCoy, ChatGPT simply made them up. Suffice it to say that the Judge was not amused.

The stories presented here have been entertaining (for us; not for Steven). Unfortunately, there’s a lot of scary stuff out there, as we will see in Part 3. In the meantime, please share your thoughts on what you’ve read here in the comments below.

4 thoughts on “Gruesome Gambols Gripping Generative AI (Part 2)”

  1. Max,

    Not even close! No wandering off into the weeds and no digressing. Definitely omitted the fashion icon bit and mom was no where to be found, let alone Genia the Gorgeous. Looks like you are safe for a couple of weeks or so…

    I used ChatGTP for advice on one of my web apps I was struggling to redesign. Damn thing presented me with code snippets in .php, .html, .js and .css that with a little tweaking (didn’t give enough detail on the request) was exactly what I needed!

    I used it to write a version of two articles for a submarine veterans newsletter I do as well. I did at least acknowledge the author, but it was not as “exciting” as the follow ups in my own style. (Personal opinion.😊) BTW, I am not a fashion trend setter as are you. But I do seem to spend a lot of time off in the weeds?

    1. Hi Fred, how can you say you are not a trendsetter while sporting that hat? Not to digress, but I last saw Deputy Dawg when I was a kid and I was unfamiliar with US accents. On re-watching it as part of this blog, I was struck by how much the little critters sounded like the guys from Duck Dynasty LOL. I’m sorry, what were we talking about….

Leave a Reply

featured blogs
Apr 16, 2024
In today's semiconductor era, every minute, you always look for the opportunity to enhance your skills and learning growth and want to keep up to date with the technology. This could mean you would also like to get hold of the small concepts behind the complex chip desig...
Apr 11, 2024
See how Achronix used our physical verification tools to accelerate the SoC design and verification flow, boosting chip design productivity w/ cloud-based EDA.The post Achronix Achieves 5X Faster Physical Verification for Full SoC Within Budget with Synopsys Cloud appeared ...
Mar 30, 2024
Join me on a brief stream-of-consciousness tour to see what it's like to live inside (what I laughingly call) my mind...

featured video

How MediaTek Optimizes SI Design with Cadence Optimality Explorer and Clarity 3D Solver

Sponsored by Cadence Design Systems

In the era of 5G/6G communication, signal integrity (SI) design considerations are important in high-speed interface design. MediaTek’s design process usually relies on human intuition, but with Cadence’s Optimality Intelligent System Explorer and Clarity 3D Solver, they’ve increased design productivity by 75X. The Optimality Explorer’s AI technology not only improves productivity, but also provides helpful insights and answers.

Learn how MediaTek uses Cadence tools in SI design

featured chalk talk

IoT Data Analysis at the Edge
No longer is machine learning a niche application for electronic engineering. Machine learning is leading a transformative revolution in a variety of electronic designs but implementing machine learning can be a tricky task to complete. In this episode of Chalk Talk, Amelia Dalton and Louis Gobin from STMicroelectronics investigate how STMicroelectronics is helping embedded developers design edge AI solutions. They take a closer look at the benefits of STMicroelectronics NanoEdge-AI® Studio and  STM32Cube.AI and how you can take advantage of them in your next design. 
Jun 28, 2023
33,516 views