Can ChatGPT Replace us All?

I doubt there’s anyone in tech, and perhaps any parent, who hasn’t heard of ChatGPT. It’s often characterized as a “robot” that can do your homework, run your business, and so forth. I’ve said in the past that I believed its responses weren’t all that sophisticated, but I didn’t offer any specific proof. Now I want to try that.

What happens if ChatGPT writes a blog on 5G? I asked it to “write a 1000 word essay on why 5G technology will not increase telco revenues” because I believe that to be true, and I wanted to see whether it would muster relevant facts. OK, I wanted to see how many of the points it made were points that I might have made, or at least would agree with. Let me start with what it came up with, in italics, and insert my own views in normal text.

5G technology is the fifth generation of mobile networks, and it promises to deliver faster internet speeds, lower latency, and more reliable connections than its predecessor, 4G. While 5G has the potential to revolutionize many industries and bring about new, innovative use cases, it is unlikely that it will significantly increase telco revenues.

One reason for this is that 5G is a capital-intensive technology, requiring significant investments in new infrastructure, such as small cells and base stations. These investments will likely decrease telco profits in the short term, as companies will need to spend large amounts of money to upgrade their networks. Additionally, competition in the telecommunications industry is fierce, and companies may not be able to recoup their investments through increased prices for consumers.

All of this is true, but it ignores the fact that the same competitive forces cited actually compel the telcos to deploy 5G. Imagine, given all the media hype about the consumer benefits of 5G, somebody decided not to deploy. It also ignores the fact that 5G offers telcos the benefit of higher user density per cell, which is important to them in managing cell density and costs.

Another factor that may limit telco revenues from 5G is the limited availability of spectrum. Spectrum is the invisible airwaves that mobile networks use to transmit data, and it is a finite resource. The limited amount of spectrum available for 5G means that telcos will need to share it with other users, such as the military or weather radar systems. This could lead to increased congestion on the network and decreased capacity, which may limit the potential for telcos to increase their revenues through 5G.

I have to disagree with this, given that spectrum is required to offer cellular services in any form. In any event, telcos have already acquired suitable spectrum in most cases, and spectrum limitations are more likely to impact new competitors; see below.

Furthermore, 5G is also expected to bring about increased competition in the telecommunications industry, as new players enter the market. Companies such as Google, Facebook and Amazon have been investing in 5G-related projects, and they may disrupt the traditional telco revenue streams by offering their own 5G services. These new competitors may offer more innovative and affordable 5G services, which could lead to a decrease in revenue for traditional telcos.

Any 5G initiatives by the new competitors are unlikely to actually be competitive with telcos. Most of these companies are really interested in promoting their tools and clouds as hosting points for 5G elements.

Another reason for this is that 5G will enable new technologies like the Internet of Things (IoT), which will make it possible for billions of devices to connect to the internet. While this has the potential to create many new revenue streams, it also means that telcos will need to handle a much larger number of devices and connections. This will likely require significant investments in new infrastructure and capacity, which may offset any potential revenue increases.

Again, I have to disagree. IoT’s multiplicity of devices is one of the reasons why more users per cell, a 5G attribute, could be important. The problem with IoT is that the great majority of IoT opportunity doesn’t require any form of mobile service at all.

Finally, 5G has the potential to increase the adoption of new business models, such as software-defined networking (SDN) and network function virtualization (NFV). These models will allow telcos to offer more flexible, on-demand services, which may lead to increased revenues. However, they also have the potential to decrease revenues by making it easier for customers to switch between providers.

Feature differentiation opportunity makes it easier to switch between providers? I don’t get this at all.

In conclusion, while 5G technology has the potential to revolutionize many industries and bring about new, innovative use cases, it is unlikely that it will significantly increase telco revenues. The capital-intensive nature of 5G, limited availability of spectrum, increased competition, and the emergence of new technologies and business models may offset any potential revenue increases. While 5G is a powerful technology, telcos will likely need to look to other sources of revenue to make the most of it.

The right conclusion, but the wrong reasons.

OK, I can’t speak for all of you, but I think that the ChatGPT response was shallow, incomplete, and sometimes inconsistent.

Suppose I change the question to add “based on CIMI Corporation views”? Here’s what I get:

It is widely believed that the rollout of 5G technology will lead to increased revenues for telecommunications companies. However, this assumption is not necessarily supported by all industry experts. The CIMI Corporation, a leading market research and consulting firm, has published a report arguing that 5G may not significantly increase telco revenues.

One of the main reasons for this is that the cost of deploying 5G networks is significantly higher than that of 4G networks. The deployment of 5G requires a much denser network of small cells, which are significantly more expensive to install and maintain than traditional macrocells. Additionally, the cost of acquiring and maintaining the necessary spectrum for 5G is also much higher than for 4G.

Another factor that may limit the potential for increased revenues from 5G is the intense competition in the telecommunications market. With many companies vying for a share of the 5G market, prices for 5G services are likely to be driven down, which would in turn limit the potential for increased revenues.

Furthermore, CIMI Corporation argues that the increased speeds and lower latency of 5G may not necessarily lead to increased demand for mobile data services. While 5G may enable new use cases such as virtual reality and autonomous vehicles, it is not clear whether these new use cases will drive significant demand for mobile data services. Additionally, many consumers may not see a significant difference in their day-to-day experience with 5G as compared to 4G, which may limit the potential for increased revenues from 5G services.

Another point from CIMI Corporation is that, 5G is not only a technology, but also a business model, and that telcos need to consider the various business models that will be required to monetize 5G services. While traditional business models such as selling mobile data plans may still be relevant, telcos will also need to explore new business models such as offering network slicing, edge computing, and other value-added services. However, it is uncertain how successful telcos will be in monetizing these new business models, which could limit the potential for increased revenues from 5G.

Overall, while 5G technology has the potential to enable new use cases and improve mobile data services, it may not significantly increase telco revenues. The high costs of deploying 5G networks, intense competition in the telecommunications market, and uncertainty surrounding the demand for 5G services are all factors that may limit the potential for increased revenues from 5G. Additionally, CIMI Corporation argues that telcos need to consider the various business models that will be required to monetize 5G services.

OK, I’m flattered by how ChatGPT characterized CIMI Corporation, and somewhat impressed that it apparently was able to actually identify and include things I’ve said. Interestingly, when asked to provide information on CIMI Corporation or me, it responded that it had no information available.

Some references to things I actually said in the past made the report a bit more consistent with my views, and this time it picked up my main point, which was that 5G needed a business model and not just a hope for one. Still, I wouldn’t be tempted to have ChatGPT write a blog for me based on my experience here. I wonder how many of you would have read, liked, or commented on LinkedIn on either of these two ChatGPT blogs?

You might wonder how this squares with the reports that ChatGPT can pass a bar exam or be used by students to write reports that, presumably, would get a decent grade. I did some other fiddling, stuff I won’t bother to repeat here, and this is what I learned.

You can ask ChatGPT a specific question in many, many, fields and get an acceptable answer. Ask it a question from a bar exam, a CPA exam, and so forth, and I think you’d likely get a decent answer. Of course, you could also do a search on the same specific question. What ChatGPT seems to me to be doing is creating a free-form answer to a question where a search would give you sources of the answer from which you’d have to pick. I think it could, properly used, do schoolwork and pass exams, but I think that its ability to actually write essays or reports is much more limited…for now.

Surprisingly, my little exercise demonstrated to me why Microsoft would want to invest in this, and why Google and others are suddenly pushing “AI”. Large Language Models like ChatGPT, fed not only text but also perhaps with things like “source credibility”, could create something that would be at least as insightful as the average human-generated document would be on the same topic. That could revolutionize searches, revolutionize education, and create all manner of opportunities and risks.

Don’t expect ChatGPT to do everything you can, in other words, but keep an eye on it over your shoulder as you advance in your career. It may be creeping up on you from behind.