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...
I just don't think the interest of the profession control. The travel agents had interests too!
Technical? Yes. Hardcore expert premium technical, no. The people who want the service can pay someone with basic to moderate skills a few hundred bucks to spend a day working on it, and that's all good.
Could I get an LLM to do much of the work? Yes, but I could also do much of the work without an LLM. Someone who doesn't understand the first principles of domains, Wordpress, hosting and so on, not so much.
They were not rotting platforms when they evaporated jobs at that particular moment, about 10-15 years ago. There's no universe where people are making money making websites. One could easily collect multi thousand dollars per month just making websites awhile ago before twitter/fb pages just on the side. There is a long history to web development.
Also, the day of the website has been over for quite awhile so I don't even buy the claim that social media is a rotting platform.