Paradigm Shifts and Changes Coming to Enterprise Software. GTP-3 and ChatGPT Jan 7, 2022
This is an experiment with Chat GPT.
“Most software today is very much like an Egyptian pyramid with millions of bricks piled on top of each other, with no structural integrity, but just done by brute force and thousands of slaves”
Alan Kay, 2004
There is clearly a shift going on in computing and software development.
Over the last 3 years, the creation and development of generative technologies has shown that given a large language model, it is possible to generate code and code snippets with the technology. It’s all also possible to check existing code and how it works with libraries. Microsoft launched the first commercial version of this concept with a tool called Code Pilot which is in production today.
“super excited about copilot and optimistic that we (the field) will be able to do 3 things more impressive than this by the mid 2020s” Sam Altman June 2021
Open AI released chat GPT in the first week of December of 2022 and it immediately started being tested for use in software development and the support of software development.
There were instantaneous responses both positive and negative over these developments.
I wrote a quick summary this morning about another post on LinkedIn by a professional software engineer who laid out 10 different uses of chat GDP in coding. He is sold on the practice. Note, he is an ML developer, so both knowledge and bias at play here.
In his description of developing code with support from ChatGPT, I found reasonable and correct. I then extended the communication about the shift in software development approaches as a message to CIOs and CTOs That’s recommended that they should explore these new GPT and LLM technologies.
The Experiment
The experiment part of this now is taking the two sets of analysis that I created and then running that through chat GTP to get extended suggestions on how to explore the impact of gender of technologies on software development. It was fast and simple like asking me a smart research assistant to suggest things to me. In my curiosity about the paradigm shift that’s occurring. It offered books on request as well as podcast and blogs. In the case of the books, I’d read half of them and will read the other half because of that. In the case of the blogs and conferences again, I know about half of them but not the others. This is an indication that using ChatGPT to explore new information is useful. And I’ve got some reading to do as well listening.
Here’s the experiment in ChatGPT.
It is unedited. All errors are my own.
— —
Open sidebar
Software Industry Trends
Rob Tyire “Act as a software industry analysts presenting new ideas like a consultant would"
Sure! As a software industry analyst, I have identified several new trends and ideas that I believe have the potential to drive significant disruption and innovation in the industry.
- Low-code and no-code platforms: Low-code and no-code platforms allow developers to build software applications without having to write traditional code. This has the potential to democratize software development, making it easier for non-technical individuals to build custom applications and for businesses to build and deploy software solutions faster.
2. Artificial intelligence and machine learning: AI and ML are transforming the way software is developed and used, enabling applications to become more intelligent and able to learn and adapt over time. This has the potential to revolutionize industries from healthcare to finance, as well as drive significant efficiency gains for businesses.
3. Cloud-native architecture: Cloud-native architecture is a design approach that leverages the benefits of cloud computing to build highly scalable, resilient, and flexible applications. This approach has the potential to significantly reduce the time and cost of developing and deploying software, and is becoming increasingly important as businesses look to leverage the power of the cloud.
4. Blockchain: While still in the early stages of adoption, blockchain technology has the potential to disrupt a wide range of industries by enabling secure, decentralized networks for storing and exchanging data and value.
5. Internet of Things: The Internet of Things (IoT) refers to the growing network of connected devices that are capable of transmitting and receiving data. This trend has the potential to drive significant innovation in a wide range of industries, from manufacturing to healthcare, as it allows for the creation of new applications and services that were previously not possible.
Rob Tyrie
“Broadened thinking on usage in usage of ChatGPT is below. It’s thoughtful work from Santiago Valdarrama . --- #iaadvice Be wary of simplistic criticisms that block use of new tools. I have already seen too much quick dismissal of generative tech because it makes errors and it’s not perfect and easy to use for anyone. This wave of change in programming has been years in coming. It’s a evolution of software engineering. Using GPT and related LLMs to develop requirements, design, code, testing, from the unit, to sub system to systems... is a paradigm shift. I have been through other shifts. Based on history, paradigm shifts are messy and there are winners and losers. There will be arguments and debates. There will be hype and there will be vaporware. This one is coming fast and some of the changes are a magnitude of differences in the way software and systems are created. In this change, the conversational element to the new tech is as important as how the generation works. Conversing with AI assistants is a skill. It is a new human-computer interface. I am advising the CIOs and CTOs I am supporting to start experiments and education this year with OpenAI APIs, ChatGPT and Alphacode (if you can get early access) and get your smart people on this. 2024 budgets for leading financial and insurance companies will have $MMs set aside to enter this shift and it will be part of any large digital transformation project. Other sectors, like entertainment and media will move faster than FSI. It is likely, your first projects will be in marketing and sales... and all the actors who help in between the Business and IT will be served greatly in this paradigm shift. You will be selecting new tech and software of advanced companies and you will have to be able to do due-dilligence on them. There will be challenges here. I recommend, that, like is done with Open Source, that you demand all vendors be transparent and disclose if they are using GPT and LLM AI in the software and services you are buying. Verticalization of horizontal tech will be a key usage of generative conversational platforms. I can’t imagine an IDE that will not add this support to environments to handle the complexities of designers and developers and QA using libraries and frameworks to deliver stable systems. The business knows how slow it is to get completed systems, what they don’t understand is how repetitive systems work can be. The shift will echo the outsource movement in the 90s, except this time parts of the work will be outsourced to AI assistants. This is the future of computing. It’s just an evolution. The time frame... is a few years, not a decade from now. Generative Tech will be joined with new symantic and symbolic computing to handle parts of this shift. Keep "Hybrid AI" and "Explicable AI" on your watchlist. #design #education #experience #cio #cto #chatgpt #openai #google #meta #microsoft “
ChatGPT:
Thank you for sharing this insight on the potential future of generative technologies like ChatGPT and the impact they may have on software development. It is certainly an exciting time in the industry, and it will be interesting to see how these technologies evolve and are adopted by businesses.
It is important to approach the use of these technologies with caution and to carefully consider the potential implications and challenges that may arise. Ensuring transparency and disclosure from vendors will be crucial in building trust and confidence in these technologies.
It is also important to recognize that the adoption of these technologies may bring significant change to the way software is developed, and it will be important for businesses and individuals to adapt and stay up-to-date with the latest developments. Continuing education and experimentation will be key in helping businesses and individuals navigate this shift and take full advantage of the opportunities that these technologies present.
What are 5 books related to this topic?
"Superintelligence: Paths, Dangers, Strategies" by Nick Bostrom: This book discusses the potential future development and impact of artificial intelligence, and considers the potential risks and benefits of such technology.
"The Singularity Trap" by Federico Pistono: This book explores the potential risks and unintended consequences of emerging technologies, including artificial intelligence and machine learning, and offers suggestions for how to mitigate these risks.
"Life 3.0: Being Human in the Age of Artificial Intelligence" by Max Tegmark: This book discusses the potential future of artificial intelligence and its implications for humanity, and considers the ethical and moral questions that arise as we move towards a future with increasingly advanced AI.
"The Age of Spiritual Machines: When Computers Exceed Human Intelligence" by Ray Kurzweil: This book discusses the potential future of artificial intelligence and its impact on society, including the potential for AI to surpass human intelligence and transform the way we live and work.
"Our Final Invention: Artificial Intelligence and the End of the Human Era" by James Barrat: This book explores the potential future of artificial intelligence and its potential to transform society, and considers the risks and implications of such technology for humanity.
What podcasts are related to this topic
Here are five podcasts that discuss topics related to artificial intelligence and machine learning:
"Talking Machines": This podcast explores the latest developments in artificial intelligence and machine learning, and features interviews with leading experts in the field.
"Data Skeptic": This podcast covers a wide range of topics related to data science and machine learning, and features interviews with industry experts and researchers.
"The AI Alignment Podcast": This podcast focuses on the alignment problem in artificial intelligence, which refers to the challenge of ensuring that AI systems behave in ways that are aligned with human values.
"The Machine Learning Guide": This podcast covers a range of topics related to machine learning, and features interviews with leading researchers and practitioners in the field.
"Artificial Intelligence in Industry": This podcast discusses the practical applications of artificial intelligence in various industries, and features interviews with industry leaders and experts.
What blogs are related to this topic
Here are five blogs that cover topics related to artificial intelligence and machine learning:
"DeepMind": This blog is published by DeepMind, a leading research organization focused on artificial intelligence and machine learning. The blog features posts on a wide range of topics related to AI and ML, including research updates, industry trends, and more.
"Machine Learning Mastery": This blog is written by Jason Brownlee, a researcher and machine learning practitioner. The blog covers a wide range of topics related to machine learning, including tutorials, tips, and industry news.
"The Wild Week in AI": This blog, published by the folks at The Waveform, covers the latest developments in artificial intelligence and machine learning. The blog features a weekly roundup of news and articles from around the web, as well as original content.
"Data Science Central": This blog covers a wide range of topics related to data science and machine learning, and features articles, tutorials, and industry news.
"Artificial Intelligence – MIT Technology Review": This blog, published by the MIT Technology Review, covers the latest developments in artificial intelligence and its impact on society. The blog features articles, interviews, and more.
What important conferences are related to this topic?
There are many conferences that focus on artificial intelligence and machine learning, including:
NeurIPS (Neural Information Processing Systems): This is a leading conference in the field of machine learning and artificial intelligence, and is held annually in December.
ICML (International Conference on Machine Learning): This is another leading conference in the field of machine learning, and is held annually in the summer.
CVPR (Computer Vision and Pattern Recognition): This conference focuses on the field of computer vision, which is a subfield of artificial intelligence that deals with the automated analysis and interpretation of visual data. It is held annually in the summer.
ICLR (International Conference on Learning Representations): This conference focuses on the field of deep learning, which is a subfield of machine learning that involves the use of neural networks to learn complex patterns in data. It is held annually in the spring.
AAAI (Association for the Advancement of Artificial Intelligence): This conference covers a wide range of topics related to artificial intelligence, and is held annually in the winter.
Organize and edit the following for clarity and begin with a clear summary in the voice of an Economist article "Broadened thinking on usage in usage of ChatGPT is below. It's thoughtful work from Santiago Valdarrama . --- #iaadvice Be wary of simplistic criticisms that block use of new tools. I have already seen too much quick dismissal of generative tech because it makes errors and it's not perfect and easy to use for anyone. This wave of change in programming has been years in coming. It's a evolution of software engineering. Using GPT and related LLMs to develop requirements, design, code, testing, from the unit, to sub system to systems... is a paradigm shift. I have been through other shifts. Based on history, paradigm shifts are messy and there are winners and losers. There will be arguments and debates. There will be hype and there will be vaporware. This one is coming fast and some of the changes are a magnitude of differences in the way software and systems are created. In this change, the conversational element to the new tech is as important as how the generation works. Conversing with AI assistants is a skill. It is a new human-computer interface. I am advising the CIOs and CTOs I am supporting to start experiments and education this year with OpenAI APIs, ChatGPT and Alphacode (if you can get early access) and get your smart people on this. 2024 budgets for leading financial and insurance companies will have $MMs set aside to enter this shift and it will be part of any large digital transformation project. Other sectors, like entertainment and media will move faster than FSI. It is likely, your first projects will be in marketing and sales... and all the actors who help in between the Business and IT will be served greatly in this paradigm shift. You will be selecting new tech and software of advanced companies and you will have to be able to do due-dilligence on them. There will be challenges here. I recommend, that, like is done with Open Source, that you demand all vendors be transparent and disclose if they are using GPT and LLM AI in the software and services you are buying. Verticalization of horizontal tech will be a key usage of generative conversational platforms. I can't imagine an IDE that will not add this support to environments to handle the complexities of designers and developers and QA using libraries and frameworks to deliver stable systems. The business knows how slow it is to get completed systems, what they don't understand is how repetitive systems work can be. The shift will echo the outsource movement in the 90s, except this time parts of the work will be outsourced to AI assistants. This is the future of computing. It's just an evolution. The time frame... is a few years, not a decade from now. Generative Tech will be joined with new symantic and symbolic computing to handle parts of this shift. Keep "Hybrid AI" and "Explicable AI" on your watchlist. #design #education #experience #cio #cto #chatgpt #openai #google #meta #microsoft
According to Santiago Valdarrama, a shift is occurring in the field of software engineering towards the use of generative technologies like ChatGPT and related LLMs (Language Model). This paradigm shift, which is happening quickly, will bring about significant changes in the way software and systems are created. In order to prepare for this shift, CIOs and CTOs are advised to begin experimenting with and educating themselves on OpenAI APIs, ChatGPT, and Alphacode. This shift will also bring about new challenges, including the need to do due diligence on new technology and software from advanced companies and the importance of demanding transparency from vendors on the use of GPT and LLM AI in their products. This shift is expected to occur within the next few years, and will be driven by advances in generative tech, semantic and symbolic computing, and hybrid and explicable AI.
ChatGPT Dec 15 Version. Free Research Preview. Our goal is to make AI systems more natural and safe to interact with. Your feedback will help us improve.
