I am a Prompt addict

The other day I had a nightmare. I woke up in the middle of the night, my heart was pounding. In my dream, Anthropic released Claude Opus 6. The problem was that it was much worse than Opus 5.5. I was so terrified, I didn’t know what to do. How will I develop software now? For almost a year now, I have been leveraging LLMs during my work and while developing my side projects. At first, I was hesitant to use LLMs, but then I gave in to the vibes, embraced exponentials, and forgot that the code even exists. 1 I still go back and forth between whether AI is good, or I’m simply digging my own grave. And despite the fact that I can finally build the things I never had time to build, I keep reflecting on what LLM usage does to me. The first, and most obvious change is that despite the fact that AI promised less work, I work much more. Recently, I saw a blog post by Orestis Ioannou titled AI Promised Less Work. I Have Never Worked More, and I agree 100%. It’s just the nature of the work…