We often talk about GenAI as it is going to replace us. Well, maybe it will, but given what I saw in programming, it will not happen tomorrow. GenAI is good at supporting and co-piloting human programmers and software engineers, but it does not solve complex problems such as architectural design or algorithm design.
In this article, the authors pose an alternative thesis. They support the thesis that GenAI should challenge humans to be better and to unleash their creativity. In this piece, the authors identify the use of AI to provoke things like better text headlines for articles, identifying non-tested code, dead-code or other types of challenges.
They finish up the article with the thesis that we, universities, need to be better at teaching critical thinking. So, let’s do that from the new year!
In this time just before X-Mas, I sat down to read the latest issue of the Communications of the ACM. There are a few very interesting articles there, starting from a piece from Moshe Verdi on the concept of theoretical computer science, through an interesting piece of text on artificial AI to a very interesting article that I’m writing about now.
The starting point of this article is the fact that we, software engineers, are taught that we should talk to our customers, discover requirements together with them and validate our products together with them. At the same time, we design AI Engineering software without this in mind. A lot of start-ups (I will not mention any, but there are many) rush into providing tools that use LLMs to support software development tasks such as programming. However, we do not really know what the developers want.
In this article, they present a survey of almost 1,000 developers on what they want. Guess what – programming is NOT in the top three on this list. Testing, debugging, documentation or code analysis are the top requests. The developers enjoy creating code, what they do not enjoy is finding bugs or testing the software – it takes time and is not extremely productive. Yes, it feels great what you find you bug and yes, it feels great when the tests finally pass, but it feels even greater when you work on new feature or requirement.
We follow the same principle in Software Center. When creating new tools, we always asks the companies what they really need and how they need it. Now, we work on improving the process of debugging and defect analysis in CI/CD. We started by a survey. You can find it here. Please register if you want to see the results of the survey – and contribute!
With this, I would like to wish you all a Merry Christmas and a Happy New Year. Let’s make 2025 even better than 2024!
I’m a big fan of Yuval Noah Harari’s work. A professor who can write books like no one else, one of my role models. I’ve read Sapiens, Homo Deus and 21 Lessons… now it was time for Nexus.
The book is about information networks and AI. Well, mostly about the information networks and storytelling. AI is there, but not as much as I wanted to see. Not to complain, Harari is a humanist and social scientists, not a software engineer or computer scientists.
The book discusses what information really is and how it evolves over time. It focuses on storytelling and providing meaning for the data and the information. It helps us to understand the power of stories and the power of information – one could say that the “pen is mightier than the sword”, and this book delivers on that.
I recommend this as a reading over X-Mas, as the holidays are coming.
Quantum computing has been around for a while now. It’s been primarily a playground for physicists and computer scientists close to mathematics. The major issue was that the error rates and instability of the quantum bits prevented us from using this kind of paradigm on a larger scale (at least how I understand it).
Now, it seems that we are getting close to commercialization of this approach. Several companies are developing quantum chips that will allows us to use more of this technology in more fields.
The paper that I want to bring up today discusses what kind of challenges we, software engineers, can solve in quantum computing – and it is not programming. We need to work more on requirements, architecture, reuse of software and quality of it. So, basically the typical software engineering aspects.
