> whoami
Lee Hayward
HaywardGG / Vibe Coder & Gamer
online & always tinkering
./about Who's behind the builds
I'm a UK based vibe coder. AI drafts, I proof, I ship, and I hold code and copy to the same standard. I riff on domain ideas and build side projects like DomainRiff and LookMa from my own homelab.
./projects Featured builds
./stack How it gets built
./hardware The rigs behind the site
./homelab The machines that never sleep
./latest Latest on X
I have supported users on old Windows boxes, lived inside helpdesk ticket queues, taught IT to people who had never opened a file manager, and now most of my working day is a terminal and an agent. Every one of those looked like the future when it arrived. Every one looks like a museum piece now.
What has not moved is the decision. Somebody still has to say what is worth doing, notice when it is wrong, and be the one who is answerable when it breaks. A tool that types faster than me is brilliant, and it has never once told me what the right thing to build was.
The bit I did not expect is that the decisions are harder now, not easier. When an afternoon can produce a working app, choosing which one to build matters more than it ever did.
I am not nostalgic about any of it, and I would not go back to a ticket queue for anything. But if you are newer to this and quietly worried you have missed the point, you have not. The typing was never the job.
What part of the work do you think survives the next round of this?004055
instagram.com
It is the difference between reviewing one decision and reviewing two. If the agent tidies a file while it is in there and the bug survives, I am left with a diff where half the lines moved and no way to tell which half changed the behaviour. The read goes from ten minutes to an hour, and if the fix turns out to be wrong I have to back the tidy up out with it.
There is a slower cost too. The history stops being worth anything. When something breaks in three months and I go looking for the commit that did it, every commit is supposed to be one thing. A commit that is a fix plus a rename plus four files of formatting tells me nothing.
The agent is not being difficult when it does this. The tidy up is right there, it is obviously an improvement, and it has no way of knowing that the review is the scarce thing here. So the brief says what to change and it also says what not to touch while it is in there.
Does your agent ever do the job well and then helpfully ruin the diff?003033