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...
"Garbage in, garbage out", is still the rule for LLM's. If you don't spend billions training them or if you let them feed on their own tail too much they produce nonsense. e.g. Some LLM's currently produce better general search results than google. This is mainly a product of many billions being spent on expert trainers for those LLM's, while google neglects (or actively enshitifies) their search algorithms shamefully. It's humans, not LLM's, producing these results. How good will LLM's be at search once the money has moved somewhere else and neglect sets in?
LLM's aren't going to take everyone's jobs and trigger a singularity precisely because they fall apart if they try to feed on their own output. They need human input at every stage. They are going to take some people's jobs and create new ones for others, although it will probably be more of the former than the latter, or billionaires wouldn't be betting on them.