The hype around ChatGPT, the latest artificial intelligence (AI) chatbot has gotten intense in the last couple of weeks. CNET says that it’s “mindblowing.” Lifehacker called it the “coolest (and most terrifying) tech of 2022.”
All this hype made me curious as to how useful it might be to me in writing blog posts about amateur radio. So, I asked it a couple of questions. Here’s what ChatGPT generated:
Question #1: What’s the best antenna for 2-meter fm amateur radio operation?
For 2-meter FM amateur radio operation, a Yagi antenna or a vertical antenna may be a good choice.
Yagi antennas are directional antennas that can provide good gain and performance on the 2-meter band, making them suitable for long-distance communication or for reaching distant repeaters. They consist of a driven element and several parasitic elements arranged in a line, and they are relatively easy to build and tune. However, Yagi antennas can be more complex and require more space than other types of antennas, and they may not be suitable for portable or stealthy operation.
Vertical antennas are antennas that are installed upright, with the radiating element extending vertically from the ground. They can be used for a wide range of frequencies, including the 2-meter band, and are suitable for local and regional communication. Vertical antennas can be simple or complex, and they may require a ground plane or radials for proper operation. They are relatively easy to install and tune, and they can be used indoors or outdoors. However, vertical antennas may not provide as much gain as Yagi antennas, and they may not be as suitable for long-distance communication.
Ultimately, the best antenna for 2-meter FM amateur radio operation will depend on the specific needs and goals of the operator. Experimenting with different antennas and trying out different configurations can be a rewarding aspect of the hobby.
Question #2: What are the advantages of software defined radio (SDR)?
Software defined radio (SDR) is a type of radio communication system that uses software to perform the functions of a traditional hardware-based radio. SDR technology offers a number of advantages over traditional radio systems, including:
- Flexibility: SDR allows you to change the operating frequency, mode, and other parameters of the radio simply by changing the software, rather than replacing hardware components. This makes it easy to adapt the radio to different communication needs and to use it for multiple purposes.
- Cost-effectiveness: SDR can be less expensive than traditional radio systems because it requires fewer hardware components and can be implemented using off-the-shelf computer hardware.
- Compact size: SDR systems can be smaller and lighter than traditional radio systems because they don’t require as many hardware components. This makes them more portable and easier to use in a variety of environments.
- Upgradability: SDR systems can be easily upgraded and expanded by adding new software or hardware components, allowing them to keep pace with the latest technology and applications.
- Performance: SDR systems can offer improved performance compared to traditional radio systems because they can take advantage of the processing power and flexibility of software to optimize the radio’s performance for a particular application.
Overall, SDR technology offers a number of advantages that make it an attractive option for a wide range of radio communication applications. It is being used in a variety of settings, including amateur radio, military communications, and public safety, as well as in research and development.
Definite limitations
After reading these results, I breathed a sigh of relief. While these results aren’t bad, they only go so far. For example, in the response about 2-meter FM antennas, there’s no distinction between quarter-wave verticals and 5/8-wave verticals. The response to the second question is also pretty generic.
I doubt that ChatGPT is going to replace me or any other ham radio blogger. At least not any time soon. Who knows how good these chatbots will get in the next five to ten years?
Kinda reminds me of those general
technical monographs I used to read in the school library encyclopedia.
It seems based on ingesting the entire Internet, and regurgitating it on command. Kind of like Google on steroids.
It’s funny, because it reminds me of how the blogs all copy each other and produce things like ‘listicles’ — “The 5 things you need to know about SDRs!”
Some of the more interesting stuff is folks asking them to do their programming homework, or find a bug in their code, etc. Kind of like stack exchange on steroids, and without the negative social interaction that often results.
Dan,
Like many things, it depends on your expectations.
I found ChatGPT to be relatively impressive. Its ability to synthesize information and turn it into coherent English is particularly good. I found it to be generally correct but sometiimes he/she/it would provide an incorrect answer.
I asked it to tell me about Dan KB6NU and here’s what I received back:
Dan KB6NU is a blogger and amateur radio operator who runs the website kb6nu.com. On his blog, he shares information and resources related to amateur radio and technology, including articles, videos, and podcasts. He also operates a YouTube channel where he posts videos about amateur radio and other technical topics. Dan KB6NU has been involved in amateur radio for many years and is active in the amateur radio community. He has a strong interest in helping others learn about and get involved in amateur radio, and his blog and YouTube channel provide a wealth of information and resources for people interested in this hobby.
Not a word about operating CW, so clearly not a credible source :-)
73 Bob K0NR
I’m definitely soooooo much more than that. :)
Thanks Dan for running this test ChatGPT. Even before this machine learning model, companies have made progress in this regard. The AP automatically creates narratives on sports events using box scores – mostly for local events. AP and others generate stock reports and press releases similarly. You can tell when you are reading one. It’s thin, and lacking. But, to be fair, I have become very used to conversing with Google Assistant, which can quickly (and usually deeply enough for my purpose) explain thermodynamics and resitors. But it can come up with epic fails, too. ChatGPT is getting a lot of frothy publicity, and you post is a helpful as a gauge.
Here’s a good analysis of ChatGPT: What Are the New AI Chatbots For? Nothing Good.
Here’s my attempt to let ChatGPT write my blog:
https://www.k0nr.com/wordpress/2023/02/blogging-with-ai-chatgpt/
Spoiler Alert: I probably need to keep writing for a while.
Bob K0NR