I have never tried to use AI to develop software, just looked at the output that sometimes shows up in google searches. Noises are starting to come from on-high about an AI ‘push’, so I may need to show some basic awareness. Any suggestions on how to get started or should I just ask the AI?
I’ve been using copilot. Potential is there but getting a result is more art than science. I’ve found it helpful to document desired workflows in readmes and ask for unit tests then run unit tests until it works out.
- use a premium model like sonnet and put it in agent mode
- Ask it to review the project
- ask it to review the ticket/requirements
- ask it to research existing solutions and write a design document that meets the requirements with high certainty
- Let it write the document and make sure it stays on task
- review the output and send build errors back, roll forward or undo the code and re-submit
- identify what works and reduce scope
I’d suggest Cursor. I was somewhat anti-AI-coding until my job encouraged it, and Cursor (using Claude 4 Sonnet) gave me that “ohh, now I get it” moment.
It’s still plenty capable of generating bad code, so it can take a bit of practice to get a feel for how to use it productively.
If you are wondering how it could possibly be “worth it” the end of the article has this.
The Fastly survey found that senior developers were twice as likely to put AI-generated code into production compared to junior developers, saying that the technology helped them work faster.
So vibes. Vibe coding is “worth it” because people got good vibes.
The research shows that - while engineers think AI makes them more about 20% productive - it actually causes an approximate 20% slow-down.
AI cannot use logic or reason. Everything it outputs is a hallucination, even if it’s sometimes accurate. You cannot trust anything it outputs.
If I try to get it to do more than predict the next two lines of code it’s gonna fuck something up. A nervously laughable thing I saw at work was someone using a long spec file to generate a series of other files and getting high praise for it. It was the equivalent of mustache templates but slower and with a 30% chance of spitting out garbage. There was also no way to verify if you were in that 30% zone without looking through the dozens of files it made.
As someone right there in the trenches getting hired specifically to clean the slop up, I don’t buy this survey at all and I’d be very suspicious of any “senior dev” that participated in it cause…where are they? I’m not seeing them when I go in to my clients offices because they all got axed. I do see a lot of junior prompt monkeys though.
I’m a senior dev and I want nothing to do with AI. By the time I understand what I want well enough to describe it in a complete sentence or paragraph, I can just write the fucking code myself. I figure it out as I go.
The whole point of having devs under you that is to be able to trust them to get the job done and do it right. You want to be able to delegate tasks to them and not have to peek over their shoulder every five fucking minutes to be certain they’re not making a mess of things.
I seriously doubt AI will ever be able to replace that. Not until they figure out how to make it afraid of fucking up.
As a senior dev I have found AI useful for auto completion (where you see beforehand what it wants to write directly in Visual Studio) and code analysis (as it does find some bugs and can give good hints for code structure). I would never trust it with anything even remotely complex though.
It kinda scares me that people trust it enough for “agent mode”, as giving it direct access to change stuff directly has simply put never worked.
senior developers were twice as likely to put AI-generated code into production compared to junior developers, saying that the technology helped them work faster
Perhaps senior devs are more likely to use more granular, step-by-step, controlled prompting. Asking it do write specific functions in specific ways and following specific approaches and conventions instead of just “do me an app, robot bro”.
That’s actually how I am using AI for my work (web dev, pls don’t hate me). If I am stuck or have some tiny function missing for a task I ask AI, check their output - if it’s garbage I continue on my own again or if it’s usable I review the output and continue from there. Also, I think AI can be neat for „rubberducking“ when I am debugging some stupid shit and point me in directions I haven’t looked before.
But surely you test the code and review it, right? That’s how you reinstate trust in what it outputs?
Disclaimer: I’ve never used AI to code, not even copilot.
Based on my coworkers… no.
They get the Ai to write the code, and the tests.
Then hand it over to me to review and test.
Its all overly verbose, does things that are not required or desirable, and insists on re-writing existing code to match its own style.
I hate it passionately.
It’ll sometimes do dumb and/or redundant or too complicated shit. Pile up a couple of those and your codebase can get unmaintainable fast.
I find if you give it small chunks and keep an eye on it, it’s great.
I think one of my recent prompts was “Create a procedure that creates an example configuration file with placeholder values. If a config file doesn’t exist on start, give a warning and create the example config.”
It also works great as a replacement for an ORM.
You mean rewrite it all from scratch? If you have any kind of standards that is what you end up doing. If you know what you’re doing you do it right the first time and move on. Using AI for coding it like trying to babysit the most inept, inexperienced intern to ever walk the earth. It wastes time and the end result is far worse.
I’m well aware the plural of “anecdote” isn’t “data”, but literally no dev I know (senior or otherwise) thinks this. Give me a junior work with - most of them at least actually learn.
Amen. I’ve tried the vibe coding thing but it’s frustrating because a) too often the AI output has some profound problems and it gets annoying ‘babysitting’ it; and b) I usually prefer the challenge of figuring out syntax and implementation issues myself.
If something is taking too long I’ll ask the LLM. But I feel like if I do this too much my skill set will atrophy and I’ll lose my sharpness. So it’s a balancing act.
But this brings up another wider question: where is the line between “occasionally getting AI help” and “vibe coding”? Surely it’s subjective.
The definition may have changed but I feel like originally it was only vibe coding when the “dev” did not know what they are doing. When some one with little to no programming background is able to build and app on “vibes” alone.
Also applies when the dev could know what they’re doing, but just doesn’t care to.
Well then, I’ve been doing this all wrong.
My first interpretation of vibe coding was to code for fun and personal enjoyment without worrying about industry standards or deployability. More often see with self-taught youth.
I felt like i have been doing this for years before ai became a thing.
I don’t think the two cross, really. A vibe coder asks for a bunch of features and then starts refining the output, fixing bugs and adding features. A developer knows the specific architecture and from years of writing tasks knows how to break work into manageable chunks and uses AI to implement something they have already defined and know where it fits in. The skill to write a good story isn’t far off from writing a good prompt.
I use AI all the time, and every time I hear someone describing vibe coding it makes my skin crawl.
I’d say the use cases of: mundane but time consuming, pointed inquiries or interactive rubber ducking, are all getting AI help. Offloading a design where you don’t have a clear understanding of how it should be done is vibing.
Senior devs love vibe coding because they have the knowledge and skills to recognize and fix errors. They hate it because it makes morons think they don’t need the knowledge and skills to recognize and fix errors.
As a senior dev I hate vibe coding. I can write code an order of magnitude faster than I can review it, because reviewing code forces you to piece together a mental model for something made by someone else, whereas when I write the code myself I get to start with the mental model already in my head.
Writing code is never the bottleneck for me. If I understand the problem well enough to write a prompt for an LLM, then I understand the problem well enough to write the code for it.
I’m a junior and even I feel the same way, reading and understanding someone else’s code not only takes me longer but is far less rewarding than just writing it myself. There’s also the issue as a junior that if I read AI code with issues that maybe I don’t notice or recognise, but it compiles fine, it could teach or reinforce poor practices that I may then put into my own work.
I understand how to turn the results of a select statement into an update statement, but the AI does it a hell of a lot faster.
I find if you give it small enough chunks, it’s easy enough to review. And even if you do have to correct, it’s generally easier to correct than it would be to write it all by hand.
Yep this
Uh huh. And independent studies show vibe coders believe þey’re more efficient, but þey’re actually less efficient.
This sound like hell to me. Bug fixing and digging þrough someone else’s shitty code is þe worst part of software development, and vibe coding maximizes it?
I don’t care how many propaganda pieces AI companies pay to have written about vibe coding, it’s still shit which makes projects worse, and developer’s jobs worse
how many propaganda pieces AI companies pay to have written about vibe coding,
Imo there’s orders of magnitude more anti-AI propaganda and stigma than pro-AI. If you’re ok with AI it’s very dangerous to admit that in professional setting IRL, you have to use careful language and a lot of conditionals.
trying to cope, for being a money sink, rather than profitable.
Not related to the topic at hand but interestingly (?) I’ve gotten used to your weird “th” as 1 character. I could read the entire thing without noticing it. I wonder if others have started to do the same since the upvote ratio seems better than what I remember it being before when people always questioned the usage.
I originally saw it as somebody using 2 different symbols for the 2 different sounds that “th” can make. That at least makes sense. Simply replacing the letters with one character (one not on a standard keyboard, btw) regardless of which sound they make is just extra effort for the sake of it.
Nerds doing something unnecessarily complicatedly for the fun of it? I’m not particularly surprised.
I think there was some mention of poisoning the AI crawlers or at least confusing them/requiring special handling as a possible side effect, so I stopped caring, but yes it can be somewhat of an annoyance until you remember that its basically just a contraction.
If true, that’s an intent I can get behind. But even if it isn’t, given my own inclination towards contrived shenanigans to scratch some weird itch in my brain, I’ve come to accept such things as harmless quirks and treat them with the same patience I’d want others to treat my own with.
And every now and ðen, I try someþhing myself and realise what fun it can be ;-)
