[yoaviram]

It seems to me that the ongoing “vibe coding” debate on HN, about whether AI coding agents are helpful or harmful, often overlooks one key point: the better you are as a coder, the less useful these agents tend to be.

Years ago, I was an amazing C++ dev. Later, I became a solid Python dev. These days, I run a small nonprofit in the digital rights space, where our stack is mostly JavaScript. I don’t code much anymore, and honestly, I’m mediocre at it now. For us, AI coding agents have been a revelation. We are a small team lacking resources and agent let us move much faster, especially when it comes to cleaning up technical debt or handling simple, repetitive tasks.

That said, the main lesson I learned about vibe coding, or using AI for research and any other significant task, is that you must understand the domain better than the AI. If you don’t, you’re setting yourself up for failure.

[naiv]

I think it's the opposite , the better you are as a coder and know your domain, the better you can use ai tools. someone with no expertise is set up for failure

[simonw]

Totally agree. I see LLM assistance as a multiplier on top of your existing expertise. The more experience you have the more benefit you can get.

[d4rkp4ttern]

Indeed, I can predict a huge gulf between pre-vibe senior engs and post-vibe lazy learners: the seniors get massive amplification and meanwhile those on the ground floor are not learning, and even gradually loose what little they did learn

[jasonm23]

I have to add that working effectively with LLMs is a skill too, mostly in terms of prompting and system level prompts to skip _most_ of the fabrication and nonsense.

They have to be explicitly told often to keep things brief, non-fiction and non-sycophantic.

Then you still need to curate responses, but less so.

[d4rkp4ttern]

Agreed, and being productive with Claude Code and similar cli tools requires being deliberate about creating docs for background info, spec, and implementation plan, and final implementation notes.

[CompoundEyes]

Domain knowledge is key I agree. I think we’re going to see waterfall development come back. Domain experts, project managers and engineers gathering requirements and planning architecture up front in order to create the ultra detailed spec needed for the agents to succeed. Between them they can write a CLAUDE.md file, way of working (“You will do TDD, update JIRA ticket like so”) and all the supporting context docs. There isn’t the penalty anymore for waterfall since course corrections aren’t as devastating or wasteful of dev hours.

[yoaviram]

TDD seems to be a good strategy if you trust the AI not to cheat by writing tests that always pass.

[jasonm23]

You need to keep the TDD LLM and code LLM as a "ping pong pair" with you as the curator / moderator.

[mettamage]

> That said, the main lesson I learned about vibe coding, or using AI for research and any other significant task, is that you must understand the domain better than the AI. If you don’t, you’re setting yourself up for failure.

Only if you fully trust it works. You can also first take time to learn about the domain and use AI to assist you in learning it.

This whole thing is really about assistance. I think in that sense, OpenAI's marketing was spot on. LLMs are good at assisting. Don't expect more of them.

[cityofplain]

The only "overlooked" part of "vibe coding" conversations on HN appear to be providing free training for these orgs that host the models, and the environmental and social impact of doing so.