Yes, it is a waste of time right now not to use AI to write code.
It's the same category of "artisan code" like "artisan cheese": you can do it if you have a ton of free time as a hobby but other than a hobby? Not worth it.
It's the same category of "artisan code" like "artisan cheese": you can do it if you have a ton of free time as a hobby but other than a hobby? Not worth it.
How are people getting this "waste of time not to use AI" and "generates 99% of my code" level of code quality?
I know people's response will likely be something, something, "add instructions to memory to not use n+1", etc. But if the Ai wants to generate code this bad, then it represents an overall quality risk that would require an infinite memory file.
They don't know what n+1 problem is and they don't know about long-term maintainability.
overall software quality seems largely unchanged
OTOH, if someone insists on writing bad code—even after being advised otherwise—then they should expect to be out of a job.
Doesn't seem like "terminated junior developer" is the level of quality we should be accepting or promoting for AI.
In any case, the point is that low quality code shouldn't be promoted as the acceptable goal for AI.
For context, I've set up harnesses with recursive automated review loops, spec driven development, explicit lists, better models, better harnesses, formal methods tooling, etc. All of it helps, but they don't eliminate output issues. Those become very apparent when I go through the slow, manual work of deeply comprehending / validating LLM code.
And that leads me to one of three conclusions. Either my standards are achievable only by hyperintelligent programming gods, I have a skill issue using LLMs, or others aren't applying the same level of attention.
The first is obviously untrue. I meet my own standards and I'm an idiot. The second seems unlikely because I can see my competent coworkers and well-regarded people in the community discussing the same issues. So that leaves the third.
You could only argue about it when an engineer was in charge and even so when they're high up enough the pressures and incentives are to just ship fast and break stuff. Not every company can afford to be a NASA making uncrashable code that runs for 100 years and goes to pluto and all.
a) puts be ahead of those people who don't, yes b) but also diminishes my technical skills if I don't actively try to engage about what I'm "vibecoding" and proactively trying to understand it.
The big AI tech companies are still interviewing people on manual coding tasks and deep understand, which when you're vibe coding a lot, you tend to diverge from those skills, because it's just easier to use AI to "help" you a lot.
People are vibecoding to do without learning, and that's their problem, but doesn't have to be ours.
They'd still be mindlessly copying and pasting from Stack Overflow without learning if they didn't have AI.
If you have an aversion to reading code and learning from it, human or AI generated, you shouldn't be in this industry.
If you're not using AI to teach yourself new things, you're not holding it right.
If you already had a hand crafted codebase, a ton of miles on it, no real issue for a long time and customers who value some metric of quality then it might be worth crafting things by hand — if only for the bragging.