Technology

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.

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 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.

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".

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.

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.

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.

If you bring a 6yo into office and tell them to do your work for you, you should be locked up. For multiple reasons.

Not sure why they thought that was a positive comparison.

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.

As a senior dev, I agree but am impressed that you’re dealing with a functional architecture to begin with

In real code, so after the first week of development, typing really isn't what I spend most of my time on. Fancy autocomplete can sometimes be right and then it saves a few seconds, but not nearly 50-100% added productivity. Maybe more like 1-2%.

If I get a single unnecessary failed compile from the autocomplete code, it loses me more time than it saved.

But it does feel nice not having to type out stuff.

That's why all research on this topic says that AI assistance feels like a 20-30% productivity boost (when the developers are asked to estimate how much time they saved) while the actual time spent on the task actually goes up by 20-30% (so productivity gets lost).

It makes a mistake about 10 - 20 %

Anecdotally, Copilot does the reverse for me.

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 will say Claude Code may be at the fore front of AI coding assistants. It runs in your terminal. Try loading it on one of your side projects and see what you can accomplish.

Vibe coding is when you ask a chatbot to code for you, then ask it to fix the errors it generated, and repeat until you can't find any more errors. Later, someone notices that your application was coded by a chatbot, exploits one of the many security flaws, and steals all your data and credentials.

A security nightmare waiting to happen.

Vibe coding is asking gpt for code, copying it into your code environment, then telling gpt about any errors or issues. The problem is that it actually works a significant amount of the time, let's be generous and say 80%. Another 15% of the time it cannot solve a problem itself. And finally the worst possible outcome is the last 5%, where it creates a seemingly working solution that actually breaks on edge cases or has potential security issues.