I started out very sceptical. When Claude Code landed, I got completely seduced — borderline addicted, slot machine-style — by what initially felt like a superpower. Then I actually read the code. It was shockingly bad. I swung back hard to my earlier scepticism, probably even more entrenched than before.
Then something shifted. I started experimenting. I stopped giving it orders and began using it more like a virtual rubber duck. That made a huge difference.
It’s still absolute rubbish if you just let it run wild, which is why I think “vibe coding” is basically just “vibe debt” — because it just doesn’t do what most (possibly uninformed) people think it does.
But if you treat it as a collaborator — more like an idiot savant with a massive brain but no instinct or nous — or better yet, as a mech suit [0] that needs firm control — then something interesting happens.
I’m now at a point where working with Claude Code is not just productive, it actually produces pretty good code, with the right guidance. I’ve got tests, lots of them. I’ve also developed a way of getting Claude to document intent as we go, which helps me, any future human reader, and, crucially, the model itself when revisiting old code.
What fascinates me is how negative these comments are — how many people seem closed off to the possibility that this could be a net positive for software engineers rather than some kind of doomsday.
Did Photoshop kill graphic artists? Did film kill theatre? Not really. Things changed, sure. Was it “better”? There’s no counterfactual, so who knows? But change was inevitable.
What’s clear is this tech is here now, and complaining about it feels a bit like mourning the loss of punch cards when terminals showed up.
[0]: https://matthewsinclair.com/blog/0178-why-llm-powered-progra...
AI has helped me pick up my pencil and paper again and realize my flawed knowledge, skills, and even flawed approach to AI.
Now i instructed it to never give me code :). not because the code is bad, but my attempts to extract code from it are more based in laziness than efficiency. they are easy to confuse afterall ;(....
I have tons of fun learning with AI, exploring. going on adventures into new topics. Then when i want to really do something, i try to use it for the things i know i am bad at due to laziness, not lack of knowledge. the thing i fell for first...
it helps me explore a space, then i think or am inspired for some creation, and it helps me structure and plan. when i ask it from laziness to give me the code, it helps me overcome my laziness by explaining what i need to do to be able to see why asking for the code was the wrong approach in the first place.
now, that might be different for you. but i have learned i am not some god tier hacker from the spawl, so i realized i need to learn and get better. perhaps you are at the level you can ask it for code and it just works. hats off in that case ;k (i do hope you tested well!)