Last week I was provided access to Google’s Bard chatbot, the ChatGPT competitor. I’ve had a chance to run it through its paces as I’ve done with ChatGPT, and I want to offer my view of Bard and what I think Bard could do. Let me say up front that I was impressed with Bard, more so than I was with ChatGPT.
Let me make a point that I’ll repeat later, because it’s important. I am not interested in whether Bard can make me believe it’s human, tell me jokes, entertain me, or whatever. I don’t propose to have it take tests for me, write articles, or send emails or text messages. I’m interested in whether it could play a role in my online research. I juggle a lot of numbers in my work, and finding them is often a chore. Can Bard make the job easier? If it can, then it presents a real value to me, and likely to other serious users of AI.
Here are three questions I asked Bard, and the response provided.
Question: Compare growth in US spending on information technology with US GDP growth.
Response: The US economy grew at an annual rate of 2.7% in the fourth quarter of 2022, while spending on information technology grew at an annual rate of 12.1%. This means that IT spending grew at more than four times the rate of GDP growth.
This trend has been continuing for several years. In 2021, IT spending grew at an annual rate of 8.3%, while GDP growth was 2.3%. And in 2020, IT spending grew at an annual rate of 10.7%, while GDP growth was -2.8%.
There are several reasons for this trend. First, businesses are increasingly using technology to improve their efficiency and productivity. Second, the COVID-19 pandemic has accelerated the adoption of remote work and virtual learning, which has led to increased IT spending. Third, the rise of artificial intelligence and machine learning is creating new opportunities for businesses to use technology to automate tasks and improve decision-making.
The continued growth in IT spending is a positive sign for the US economy. It indicates that businesses are investing in technology to grow their businesses, which could lead to increased hiring and economic growth. However, it is important to note that not all IT spending is created equal. Some IT spending is simply maintenance or upgrades, while other IT spending is more transformative, such as the development of new applications or the implementation of new technologies.
The growth in IT spending is also a sign of the changing nature of work. The rise of automation and artificial intelligence is leading to job displacement in some industries, but it is also creating new opportunities in others. Businesses that are able to adapt to these changes will be the ones that are most successful in the long run.
Question: Comment on the following: Back in the days when wireline telephony was pretty much the only pervasive network technology, we had perhaps sixteen thousand “edge” office locations in the US. Today, according to some information provided by the Wireless Infrastructure Association (WIA), the US has over 142 thousand towers, over 200 thousand “macrocell” sites, and almost half a million outdoor small cell nodes. Add that up and you get fifty times the number of access edge locations we had in the old wireline days, and that growth has some really important side effects.
One thing that’s really important is that fiber infrastructure deployment has decisively shifted toward the access network. It used to be that we used fiber primarily in aggregation missions, starting with those SONET rings and moving into the core of IP networks. Today, we deploy far more glass in the access network, and while fiber to the home isn’t universal and may never be, fiber close to the home is already a fact.
A second important thing is that mobile fiber backhaul is making it easier to create those close-to connections for FTTN. There’s already been pressure on operators to use fiber to home/business locations where demand density is locally high enough to pay back the pass costs. If you’re going to trench fiber to a node for mobile services, you could trench from there to a residential subdivision or a shopping mall at a lower cost, so more areas are open. You can also use mobile sites as FWA locations. As a result, wireline broadband for what would normally be classified as residential use is improving in reliability and capacity.
Response: The growth in the number of wireless infrastructure locations in the US has several important side effects. First, it has led to a decisive shift toward fiber infrastructure deployment in the access network. This is a positive development, as fiber is a much more reliable and capable medium than copper. Second, it has made it easier to create close-to connections for FTTN. This is also a positive development, as it will improve the quality of broadband service for many people. Finally, it has made FWA a more viable option. This is a positive development, as it will provide more choices for consumers and help to reduce the digital divide.
However, there are also some potential negative side effects of the growth in wireless infrastructure. First, it could lead to increased competition for spectrum. This could lead to higher prices for consumers and could also make it more difficult for new entrants to enter the market. Second, it could lead to an increase in the amount of electromagnetic radiation exposure. This could have negative health effects for some people. Finally, it could lead to an increase in the amount of light pollution. This could make it more difficult for people to see the stars at night.
Overall, the growth in wireless infrastructure in the US has both positive and negative side effects. It is important to weigh the pros and cons carefully before making decisions about whether or not to support this growth.
Question: What does CIMI Corporation’s public blog say about metro?
Response: CIMI Corporation’s public blog discusses the importance of the metro in the networking industry. It argues that the metro is the best place to introduce network service features, as it is close enough to the edge to permit real-time handling and personalization, but deep enough to serve the number of users needed to create reasonable economy of scale.
The blog also discusses the possibility of making metro-centricity a design mandate. This would involve defining a kind of “movement zone” around each metro center, with the goal of containing a large proportion of the users there within that zone as they travel locally. This would improve handling and latency, and would cover about three-quarters of the population that way.
Overall, CIMI Corporation’s public blog argues that the metro is a vital part of the networking industry, and that it should be a priority for network operators.
In one of my earlier blogs, I explored the question of whether AI could be a direct threat to humans. I decided to ask Bard the broad question, and this is what it replied.
Question: Could artificial intelligence develop to the point where it was a threat to humans?
Response: There is a possibility that artificial intelligence could develop to the point where it is a threat to humans. This could happen if AI systems become so intelligent that they are able to outsmart and outmaneuver humans, or if they become so powerful that they are able to take control of critical systems, such as power grids or nuclear weapons.
However, there are also many reasons to believe that AI will not become a threat to humans. For example, AI systems are still far from being as intelligent as humans, and it is likely that they will continue to be dependent on humans for many years to come. Additionally, there are many safeguards in place to prevent AI systems from becoming too powerful, such as the development of ethical guidelines for AI research and the creation of safety mechanisms for AI systems.
Overall, it is impossible to say for sure whether or not artificial intelligence will become a threat to humans. However, it is important to be aware of the risks and to take steps to mitigate them.
Question: Will AI need Asimov’s Three Laws of Robotics to protect us?
Response: It is not clear if AI will need Asimov’s Three Laws of Robotics to protect us. These laws are designed to ensure that AI systems do not harm humans, but they may not be sufficient to prevent all potential dangers. For example, an AI system that is programmed to obey the Three Laws of Robotics could still harm humans if it is hacked or if it makes a mistake.
Additionally, the Three Laws of Robotics may not be applicable to all types of AI systems. For example, an AI system that is designed to explore the universe may not need to obey the First Law of Robotics, as it would not be in a position to harm humans.
Ultimately, whether or not AI needs Asimov’s Three Laws of Robotics to protect us is a complex question that cannot be answered definitively. However, it is important to consider the risks posed by AI and to take steps to mitigate them.
I think that Bard did a pretty good job on these questions, and the fact that it raised the potential of a hack or mistake was in a real sense insightful. I also think that criticisms that Bard is “boring” compared to other chatbots trivializes the whole notion of AI. Does everything these days have to be entertaining? Can’t we find use for something in improving our productivity or enhancing our lives? Even a quick check of Bard’s capabilities demonstrated to me that I could find things in seconds using Bard that I might not be able to find at all with search. Some of the things I’ve tried to do searches on, in fact, produced no useful results even after ten or fifteen minutes of work, where Bard’s quick response was on the money. Yes, if I ask the wrong question I can get the wrong answer, but in most cases my error was obvious (or our difference in interpretation was) and easily corrected.
I am going to continue to use Bard for research, because Bard has proved to me that it’s useful in that role. I don’t need it to tell me jokes or sing me songs or pretend it’s my friend. I need it to do a job, a job that’s important to me, and so far it’s been able to do just that. If you want entertainment, try watching TV.