As I have mentioned several times in this blog, I have been working on and teaching artificial intelligence since the beginning of my career. This drove much of my interest in cloud computing, as AI was not economically viable or accessible until the “cloud” came along.
Interest in AI and its applications was reflected about five years ago. Then the pandemic hit and part of the budget shifted to rapid cloud migrations. AI is back now that things are back to normal. Most companies have grasped the basic potential of AI and are looking to weaponize the technology for their business.
Technology has become more impressive along the way. Generative AI, for example, has become a reality accessible and free from PhD dissertations with the advent of generative AI services such as: Chat GPT.
Generative AI is a type of artificial intelligence that generates new and unique outputs such as text, images, and sounds based on input data and learned patterns. This includes tasks such as text generation, image synthesis, and music production.
Various inputs can be made via chatbots or APIs and the responses are impressive. The response has been very impressive, having responded to calls from journalists writing articles about AI replacing workers. It’s a question I’ve been asking for the last 20 years, but now with a modern twist. Colleges and universities have renewed concerns about college students using his ChatGPT and similar services to write reports. AI produces output that is not plagiarism and therefore cannot be readily identified by plagiarism detection systems.
Ethical and bias concerns in AI can arise from certain types of training data. Do these biases lead to unintended negative consequences, such as automated patterns of denying loans to certain groups?
I’m asking core questions like: What types of human tasks can AI replace now, or in the near future? Plan career transitions to jobs that AI can’t automate Do you have to? Is it safe to be a cloud computing architect, cloud developer, cloud operations engineer, devops engineer, cloud project leader, etc.? These are the job titles for most people reading this article.teeth you Are you in danger?
In reality, I think we are well on the way to replacing many human tasks with AI-powered automation. This is something that happens as technology advances and is not new. Technology has left dozens of people out of the fields to harvest crops in the fall. You can check out of the supermarket without any human interaction. Our cars and trucks can drive themselves.
One of the things I find frustrating is the lack of useful automation throughout the IT design and deployment process. Indeed, there are many tools, processes, methodologies, and other assets to accelerate your journey to optimized cloud architectures and deployments. However, it does not make decisions that are important to the architect. Cloud architecture decisions typically have to be made through deep analysis and judgment, which can only come from experience. More importantly, creativity and innovation are still needed. That is, it is man-made.
Of course, humans make many architectural mistakes, including choosing the wrong platform, tools, and services. Humans create architectures that are completely unoptimized and fail to deliver value to the business. I recently dealt with that issue.
Letting AI create solutions will probably make better decisions. What if an AI system had training data that simultaneously reflected the knowledge of thousands of talented cloud architects? Such AI systems can effectively process that knowledge into solutions based on the business and technology requirements provided to them. It may not give you the definitive answers you need to build something, but it might get you close enough to remove a lot of work and potential mistakes.
The most likely path is the continued emergence of tactical AI tools. These tools focus on specific architectural areas such as network design, database design, platform selection, cloud native design, security, governance, and container usage. Because these tools leverage near-perfect data and don’t have the pesky human frailties (feelings and emotions) that drive some architectural designs. Of course, some of these AI tools still exist today (don’t tell us about yours) and are moving towards this ideal. However, its usefulness depends on the task.
Tactical AI tools must be operated by knowledgeable people who know how to ask the right questions and validate the designs and recommendations they generate. Fewer people may be required to perform the tactical component design of a large cloud architecture, but the process doesn’t exclude everyone. Remember, many of these mistakes are made because businesses struggle to find skilled cloud professionals. Tactical AI tools could also help solve this problem by better synchronizing the supply and demand of talent.
It’s easy to predict how this will play out, and it’s not surprising. Design, development, and deployment tools evolve. They offer more value and utility.small number of people May Overall, these tools require a competent operator to function properly. They primarily focus on the tactical design of cloud he architecture components such as networking and security.
So we have to rely on people like you to build a healthy cloud solution. There may be AI solutions for smaller problems, but the larger problem of poetically automating cloud architectures remains unsolved.
I think we will need human cloud architects and solution designers for some time to put all this together and ensure we deploy an optimized solution that delivers the most value to the business. I doubt it will be completely replaced by AI, but I don’t think it’s unlikely to last forever.
But let’s ask ChatGPT: “Will AI replace cloud computing architects?”
“AI is unlikely to completely replace cloud computing architects in the near future. It requires human oversight and decision-making to ensure that systems are configured correctly and AI is working as intended Cloud architects are responsible for the overall cloud computing environment It plays an important role in strategy and design, and also in tasks that are difficult to fully automate with current AI technologies, but also in some of the repetitive and mundane tasks cloud architects perform today. AI can automate and allow us to focus on more strategic, higher-level responsibilities.”
I accept.
Copyright © 2023 IDG Communications, Inc.
