How to become a 10x ramble-coder - Moe Khalil
Moe Khalil
SubscribeSign in
How to become a 10x ramble-coder<br>Yes, your roommates will worry about you
Moe Khalil<br>Jul 23, 2026
Share
Andrej Karpathy recently tweeted about his new favorite way to work with LLMs - “a nice long ramble session”, as he called it.<br>This is something my cofounder and I have been doing for months now, and it’s such a step up from regular old typed vibe-coding that I can’t remember the last time I used my keyboard to prompt an agent. We’ve gotten worried looks from people sitting next to us at coffee shops, neighbors closing their windows because they’re trying to sleep while we ramble to Codex at 1AM, and so many more embarrassing incidents that I’d rather not remember.<br>But the thing is, it works so goddamn well. We can’t stop doing it.<br>I’ll start out by trying to explain exactly why I think this is the future of communicating with agents. Then, I’ll share some tips on how to get the most out of your rambles. All I ask is that you give it a try - I promise you will not switch back.<br>So why is rambling better than typing?
Well first of all, it’s a less lossy form of compression.<br>When prompting your agent, what you’re trying to do is translate the best representation of what’s in your head into something it can understand - language. The issue is that your train of thought - or at least mine - is constantly contradicting itself.<br>I’ll give an example. Let’s say I want to build a login screen. This is approximately what my train of thought looks like:<br>Okay, login screen. I want an email input and a password input, a sign up button and a log in button.<br>Oh and I want a way for people to recover accounts if they forget their password.<br>And people should be able to log in with Google, Github, other stuff.<br>Actually, maybe not Github. My users aren’t engineers, no need to set that up currently.<br>Although why not add it - it definitely can’t hurt<br>Oh and I want it to look good. Maybe a split screen with the log in on the right and some image on the left<br>Maybe an AI generated image - I’m not entirely sure what I want it to look like<br>Or maybe we should have it be a modal - that’s one less screen to have to take the user to<br>Oh and I also do want a log in with Facebook option, there’s some overlap there<br>What could be cool for the image is ASCII art - maybe an ASCII art city? Ugh, that’s so generic though, it should look different<br>Let’s be real though, nobody’s gonna look at the login screen. Nobody cares what it looks like. That’s just vanity<br>You know what I hate though? When a log in page makes you go to a different page for sign up. I don’t want that<br>Also can we do one time codes instead of passwords? It’s way simpler.<br>I guess I just want something simple that works.<br>[and it keeps going for a while - way too long for a login page, but I digress]<br>There’s a lot of interesting nuggets there. Things that an agent could pick up on and use to guide its decision making:<br>My users are non-technical
I care about simplicity
I don’t like redirecting users from the current page unless necessary
I don’t like generic UI
I get caught up chasing vanity sometimes
Now, let’s say I wanted to turn this train of thought into a prompt. I’d probably write something like:<br>Build a login screen with email/password fields, sign up and login buttons, password recovery, and social login (Google, maybe Facebook). Split-screen layout, image on one side. Keep it clean.<br>Notice how much nuance got lost. And that’s for an extremely simple, non-consequential decision. Imagine how much valuable information your agent is missing out on when building the core product.<br>Rambling allows the agent to get to the reasoning behind every decision. And once it understands how you reason, it gets so much better at understanding your taste, and you’ll immediately notice the number of follow-up prompts go down.<br>Okay, so rambling works. How do I ramble better?
The most important thing is to lean into your uncertainties. Your thought process behind why an alternative might not work is often way more revealing than the decision you end up making.<br>It’s the alternative-that-almost-worked that tells the agent about your constraints, not just your preferences. If we go back to the login screen example, the modal-vs-split-screen back-and-forth told the agent more about my redirect aversion than either final choice did.<br>I’d argue that this should be taken to the extreme, which is where the next tip comes in: multiplayer rambling.<br>Sometimes, my cofounder and I will have what we call “constructive arguments”. We’ll turn on the voice memo app on our phones and just start talking about everything. Technical decisions, short-term decisions, long-term decisions, what biases we have, what each one of us believes. We’ll encourage each other to disagree, because who knows what valuable nuggets could come up when we do.<br>These conversations can take hours. We’ll keep going back and forth, digging deeper on...