Learning From Breakage I've had the fortunate, or maybe unfortunate, experience of being thrown into a few jobs with no training. At a couple of my bartending jobs, I had to start working without any training, calling over someone to help run the ordering machine while I made and served drinks. I managed to slowly learn how things worked throughout that first shift, so I was ready to work on my own the second night. I had a similar experience at a tech job, starting as the lead DBA/IT Manager in a crisis, having to try and solve problems after ask others how things were supposed to work. I ended up fixing a bit of code, adjusting networking, and directing others on my first day. When we have a crisis, we often learn a lot from the situation. I've been through crashed upgrades, virus breakouts, hardware failures, and more in my career. While each was stressful and often not enjoyable, I learned a lot each time and came through the incident a more capable developer/DBA/whatever. When we work through a tough time, we are often better equipped for the next time something goes wrong. I ran across a great piece that says you never really know a system unless you've broken one. This is Tim O'Brien, a software architect who has learned a lot about databases from failure. In fact, I love his interview question for data professionals: "tell me about the worst database schema you ever created. What did it teach you to avoid?" I've certainly learned a few things over time from my schema designs, but those are stories for another piece. The piece draws parallels to today's use of GenAI technology and vibe coders who seem to have success that they highlight in posts without discussing the problems. I do believe AI technology is going to make a lot of things easier (and faster) to build and then fix when they break. And they are going to break, partially because AI tech might not do a great job, and partially because we might not direct it well enough. Clear communication is key when working with AI. I've started to build some skills with AI, but as I try to tackle more complex tasks or scale up my work, I realize that I often don't know enough about either the problem or AI technology, and I'm going to make mistakes. I'm going to break things and then have to fix them, or more likely, learn how to get the AI to reduce the number of broken things in some way before I have to take over. And learning to take over might be the number one skill with AI tech, but that's something that you will only learn from the AI not working well for you in a variety of situations. Steve Jones - SSC Editor Join the debate, and respond to today's editorial on the forums | 
