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...
Desktop publication software killed many jobs. I worked for a publication where I had colleagues that used to typeset, place images, and use a camera to build pages by hand. That required a team of people. Once Quark Xpress and the like hit the scene, one person could do it all, faster.
In terms of illustration, the tools moved from pen and paper to Adobe Illustrator and Aldus / Macromedia Freehand. Which I'd argue was more of a sideways move. You still needed an illustrators skillset to use these tools.
The difference between what I just described and LLM image generation is the tooling changed to streamline an existing skillset. LLM's replace all of it. Just type something and here's your picture. No art / design skill necessary. Obviously, there's no guarantee that the LLM generated image will be any good. So, I'm not sure the Photoshop analogy works here.