If I had said this post’s title out loud twenty years ago, I don’t believe I would have lasted this long in the market. But right now… there is nothing wrong with it. AI era. The game changed.
I can also say that over my career I lost count of how many times I maxed out my hardware. Yet I was genuinely surprised the day I discovered that 64 GB wasn’t enough for me anymore — and neither was a single graphics card, with even my Claude Max plan (5x) hitting its limits. I had to adapt.
Let’s be clear: this website I built on Dev. We are talking about a static website. The images, however, are another story — those I had to build on Prod. When we talk about developing a real system, I see no other choice but to use my best GPU hardware.
How Claude and the dragons talk
The two machines live in different buildings and share no LAN — every packet between them rides the tailnet:
Two dragons, one workload
In the end, AI really did demand more hardware for us developers to produce more. Using Fable Max (5x) to plan and orchestrate, and the Qwens to develop — while keeping balance within my human limitations — I can go up to three consoles at the same time without exceeding anything. And that is great!
However, effectively using something is different from just using something. Effectively producing AI software became a new technique of its own. Why do I say so? Because — I asked Claude:
"By using qwen the way we are, are we really minimizing Fable usage?"
Honestly? Only partially — and for today's workload, probably not much.
"Which change made the most effective use of it today?"
Most effective: the /search feature. Solidly effective: the coordinated multi-edit content changes. Not effective: the one-liner loop — the panel width dance (18rem → 24rem → 28rem).
Besides that, you also have to learn how to maximize the 24h usage of your Claude plan while living your personal life — but that is too much for today!