I used to do very basic "script-kiddie" coding about 30 years ago, but haven't really done any coding since then. Until about 6 months ago when I started being able to use LLMs to vibe-code. I speak my ideas and LLMs do a remarkable job of creating them.

I understand enough logic and basics of common programming language structures (e.g., functions, variables, loops) to be able to do a little creating on my own and some editing of what LLMs create, but LLMs are good at correcting themselves if I have a little patience and ask them to iterate for a while (usually with a guided goal).

It's absolutely remarkable that this technology exists in my lifetime. I feel like we're way closer to Star Trek's "Computer, do this thing" than I ever thought I'd actually see.

Sometimes I let the LLM choose the stack to use and sometimes I tell it what I want. But how far away are we from lanugages not mattering at all? How long until I say "make a program that does X and host it here" and LLMs use

Vibecoding as a term is only a month or so old--but I think it captures a new and significant shift in the way we might approach coding now and in the future.

Andrej Karpathy tweeted (Xed?) about it here:

There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask

I'm enjoying the challenge of using these high-level editors. They don't always do what I want. But many times, they explore possibilities I never would have considered.

Currently, I'm giving Windsurf a try, both in my personal projects and at work. I really like the Cascade process, where it tries something, then realizes it could do a bit more, then tries an alternate path, etc. It's a little easier for me to work with than Cursor, although I haven't used Cursor in a couple of weeks--so maybe it's already improved lol.

I tried working with dual Windsurf windows open today--the idea was: could I manage two "AI agents" as they try each to solve a different problem? I had one exploring a bug: first, chatgpt 4o helped convert screenshots of the issue to text, then I pasted all of the notes our product manager had made (along with the screenshot-to-text) and had Windsurf noodle on that for a bit. It came very close to a solution, but the tests were unable to prove the solution worked, s

I showed my 15yo daughter what I was doing (building https://vibe-coders.org/) and she immediately saw promise it in to build her own health app and schedule her own exercise routine in the morning.

Within a few minutes she'd created a prompt that generated a website just for her--no login, no sharing her data. She made flowers grow out of the corners when she loads the website, just for a personal touch. She can add scheduled weekly exercises and then check them off on a daily basis when she does them.

Super cool!