I tried leaning in

These posts like the one OP made is why I'm losing my mind. Like, is there truly an agentic way to go 10x or is there some catch? At this point while I'm not thrilled about the idea of just "vibe coding" all the time, I'm fine with facing reality. But I keep having the same experience as you, or rather leaning more on that supercharged Google/SO replacement or just a "can you quickly make this boring func here that does xyz" "also add this" or for bash scripts etc. And that's only when I've done most of the plumbing myself.

The thing is, using an agent or AI to code for you is a learned skill. It doesn’t come naturally to most people. For you to be successful at it, you’ve got to adopt a mentor / lead mindset - directing vs doing. In other words, you have to be an expert at explaining yourself - communicating clearly to get great results. Someone who hasn’t got any experience coding, or leading in any capacity, anywhere in life (or mentoring) will have a hard time with agentic development. I’ll elaborate a bit more - the ideal mindset requires fighting that itch to “do it yourself” and sticking to the prompts for any changes. This habit will force you to get better at communicating effectively to others (including agents).

I don’t vibe code yet but it has sped me up a lot when working with large frameworks that have a lot of magic behind the scenes (Spring Boot). I am doing a very large refactor, major version spring boot upgrade, at the moment. When given focused questions for parts of the code it it will give me 2-4 different approaches extending/implementing different bean overrides. I go through a cycle of back and forth having it give me sample implementations. I often ask what is considered the more modern or desirable approach. Things like give me a pros and cons list of the different approaches. The one I like the best I then go look up the specific docs to fact check a bit. For this type of work it easily is a 2-3x. Spring specifically is really tough to search for due to its long history and large changes between major versions. More times than not it lands me on the most modern approach for my S…

If you have not started working on a new codebase while adopting AI, it may be harder to realize the gains. I switched jobs somewhat recently. At my previous job, where I was on the codebase for years, I knew where the changes should be and what they should look like. So I tried to jump directly to implementation with the AI because I didn't need much help planning and the AI got confused and did an awful job. In a new codebase, where I had no idea how things are structured, I started the process by using AI to understand where the relevant code is, the call hierarchies and side effects, etc. I have found by using the AI to conduct the initial investigation, it was then very easy to get the AI to generate an effective spec, and then it was relatively easy to get the AI to generate the code to that spec. That flow works much better than trying to one shot implementation

How are you guys using LLMs? I've done a couple of applications for my own use, including a "Mexican Train Dominoes" online multiplayer using LLMs and it doesn't stop amazing me, Gemini 3 is crazy good at finding bugs at work, And every week there are very interesting advances in Arxiv articles. I'm 45 years old, have been programming since I was 9, and this is the most amazing time to be building stuff.

Don't be put off forever by one bad experience with Cursor. Gemini 3 would likely yield much better results now.

IME vibe coding works spectacularly for simple one-off scripts that do a fairly simple thing. I can describe the work in ~10 minutes and save 2-4 hours of scripting. Just last weekend I wanted a script to process a csv file and produce some reports and graphs out of that. I think it would've taken me the 2-4 hours to write it myself. Instead, I had cursor write it while waiting for boarding at the airport, probably no more than 10 minutes. For codebases anything more complex than that, it starts to fall apart pretty quickly. In that scenario it works ok only if I do all the work of designing the system and the functions and only let it type in the code for individual strictly-defined functions. So it does save some work which is nice, but it's not a huge win.

When they say skill issue, they mean it. Have you spent at least 4-5 hours on specs (mermaid, markdown)?