Right, remember how in ~2023 "prompt engineering" was ostensibly the critical thing everybody "needs to learn now or get left behind"?
I feel these tools—or at least the business-model behind them—have a pattern: Basic adoption is easy, while protecting yourself against their flaws is a shifting target where expertise goes stale.
1. Other humans also review my code and I know they won't approve until they're ok with it anyway.
2. I don't trust that the verifications we have at the moment are good enough to catch the errors LLMs still make.
So trust me, I'm not a "vibe coder"
But I can see the writing on the wall. We're not really maximising the potential of these things by doing it this way. In my particular industry, we're in an arms race for clients who can easily move to a competitor. So we need to be continually improving. How I predict this unfolding is that we'll need to get much better at verification of correctness (functional and non-functional) and once that is satisfied, humans will stop manually writing and reviewing code, otherwise you'll just lose to your competitors. At least in my industry, maybe not all.
This also used to be my line of thinking too. I started going down this road. Then I stopped because I realised for this to really work you need the whole team to buy into it and then be competent at it, including product managers. I think it's more or less above the skill floor of the average engineer, so trying to actually implement it in a team is going to be painful. For sure I think some people will go down this road, but I think the vast majority actually will not.
I don't really buy it actually. There isn't really anything meaningful you can learn with how to use LLMs/agents that has a half-life greater than a few months at this point, so you can just start doing it at any point in the future and not be meaningfully left behind. On the other hand years of letting your actual engineering skills atrophy will have a negative effect on you. I've been witnessing the effects of this. Going back to more coding by hand with AI-assistance circa the 2023 era as a happy medium. I think this is the sweet spot. Full agentic engineering has nasty failure modes and in the long-term is kind of a bad option for basically everyone. I say this after having done it for almost a year at this point, and transitioning away from it now.