I always wonder when people can sell ideas or products so effectively.
565 karma · joined January 11, 2020
Founder of https://playcode.io - ai native website builder.
I always wonder when people can sell ideas or products so effectively.
My point to help to build your own MentalOS that works for, to live smoother lives without huge up and downs.
I even build a custom AI therapy tool for myself.
I'm a solo founder, and for most of my adult life, I've been trapped in a brutal cycle: intense productivity followed by total burnout. I'd work 16-hour days, feel like a god, ship amazing things, and then crash for weeks, feeling depressed and anxious, unable to even look at code. My relationships would suffer, my health would tank.
I tried everything: timers, discipline, willpower, blocking apps. Nothing worked. My "Operator" self would always find a way around the rules my "CEO" self made.
Recently, I finally figured out the underlying pattern. It turns out I was managing my addictions all wrong.
Addiction 1: The Builder's High (High-Calorie Flow)
This is the one we all know. That state of deep focus when you're coding, solving a hard problem, or even gaming. The world disappears. Time melts away. It feels incredible. It's a powerful, productive high.
The Trap: I was using it as an escape. Whenever I felt anxious, bored, or had a fight with my wife, I'd retreat into "Work Sleep." It's a state like a deep trance where you're not even consciously choosing to ignore the world; you're just gone. The problem is, this flow is like eating nothing but sugar. It's high-calorie, gives you a huge rush, but it's not sustainable. It burns you out, leaving you with a massive energy debt.
Addiction 2: The Player's High (Nutrient-Dense Flow)
This was my big realization. I needed a second addiction, but a different kind. This isn't just "go to the gym" (I call that "Joyless Exertion"). This is about finding a physical skill that is engaging, challenging, and autotelic (fun for its own sake).
For me, this has been things like mountain biking, learning trampoline tricks, skiing, or karting.
This type of flow is different. It's nutrient-dense. It doesn't drain my energy; it rebuilds it. After a long bike ride, I feel energized and clear, not depleted and foggy.
The Second Trap: But I was misusing this one, too. I have a lifelong pattern I call the "Flow Addiction & Burnout Cycle" for my hobbies:
Discover: Find a new, exciting sport.
Master: Get obsessively good at it, fast.
Boredom: My skills surpass the safe challenges available. It stops being fun.
Escalate Risk: To chase the original high, I start doing stupid things—skiing off-trail in a storm, riding my motorcycle way too fast.
Crash: Inevitably, I get injured or have a near-death experience.
Abandon: I drop the hobby, now tainted with trauma, and find myself with no way to rest.
The Solution: The Dance
The goal isn't to cure these addictions; it's to manage them as a system.
Recognize the difference: Know when you need a "Builder's High" to be productive and when you need a "Player's High" to recover.
Become a "Professional Amateur": I now keep a portfolio of 2-3 physical hobbies. I enjoy the steep part of the learning curve and deliberately switch before I hit the mastery ceiling and start escalating risk.
Safety Check First: Never use high-risk physical activity to fix burnout. You're depleted, and you'll crash. You can only play hard when you are rested.
I'm learning to dance between these two addictions. One builds my product, but the other rebuilds me. For the first time, it feels like I have a sustainable way to be a 10x programmer without destroying my life.
Hope this helps someone else.
Now I love dictating by voice instead of typing. It used to seem that typing was so easy—so “easy”—and thanks to ten-finger typing everything happened very quickly. But compared to what you can rattle off by voice, it’s like night and day.
And those dashes the transcription adds, of course—they look completely out of place.
Tell us what you do—how, under what conditions, and in which programming languages. What exactly makes it better? Does it just search for files? Well, that’s hardly objective.
So far the impression is… well, you say it only seems better. But you won’t get far with that kind of reasoning.
Objectively, it now seems to me that Claude the cat is better, because everyone around says it’s better. Yet no one has actually explained why. So the hype is inflated out of thin air, and there are no objective reasons for it.
I have a monorepo, so different instructions and rules live in different corners of it, which I manually add as needed. Doing all this with Claude is hard: it kind of works, but it’s a kludge. It’s much easier to manage through the UI. As the saying goes, it’s better to see something once than to remember it ten times, type a command, and configure it.
I can say the same about Vim and Emacs users. No one has yet proven to me they can code and navigate faster than an ordinary programmer using a trackpad or a mouse and keyboard. It’s purely a matter of taste. I’ve noticed that people who love those tools are just bored at work and want to entertain their brains. That’s neither good nor bad, but it doesn’t give a real boost.
By the way, there’s a study (a bit old, admittedly) showing that working with an LLM still doesn’t provide a massive speed-up in programming. Yes, it spits out code quickly, but assembling a finished result takes much longer: you have to review, polish, start over, throw things out, start again. It’s not that simple.
Speaking of Claude, he’s a real master at shitting in the code. At the speed of sound he generates a ton of unnecessary code even when you ask him not to. You ask for something minimalist, nothing extra—he still slaps on a pile of code with useless tests that outsmart themselves and don’t work.
That’s the downside. Overall, it’s easier to program when you just say what to do instead of sitting there straining your own brain. But even then it’s not simple. If you yourself haven’t figured out very carefully what you’re doing, you’ll end up with crap. I almost always throw away what I wrote with an LLM when I was tired. I don’t think there’s ever been an exception.
The only way to write something decent is to dig in thoroughly: draw diagrams, write everything out, and only then tell the LLM exactly what to do. Then double-check, make sure it didn’t write anything extra, delete the excess. And only like that, in small chunks. The “make me a feature, I pressed a button and walked away” mode doesn’t work if the task is even slightly complex.
Yeah, I got carried away—had to let it out. I have a lot to say about LLMs and programming with them, and not just about Cursor and Claude. The tools completely upended the way we program...
Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. First, the whole process takes a hell of a lot of time. Second, the learning curve is steep: you have to work through the terminal and type commands.
And the outcome is exactly the same as with the Claude that’s built into Cursor—only slower, less clear, and the generated code is harder to review afterward. I don’t know… At this point my only impression is that all those influencers in the comments are either sponsored, or they’ve already shelled out their $200 and are now defending their choice. Or they simply haven’t used Cursor enough to figure out how to get the most out of it.
I still can’t see any real advantage to Claude Code, other than supposedly higher limits. I don’t get it. I’ve already paid for Claude Code, and I’m also paying for Cursor Pro, which is another $200, but I’m more productive with Cursor so far.
I’ve been programming for 18 years, write a ton of code every single day, and I can say Cursor gives me more. I switch between Gemini 2.5 Pro—when I need to handle tasks with a big, long context—and Claude 4.0 for routine stuff.
So no one has convinced me yet, and I haven’t seen any other benefit. Maybe later… I don’t know.
"I know developers never pay, but why?"
Anything else marketing staff.
Just curious.
Interesting. Looks like Chrome just fixed energy issues with their app to keep up with Safari?
Anyway, they don't say anything about brightness and number before fixes, yeah.
But it is just wishes. Nice work!
Also, soon there are will be feature to send "news alerts" right to Slack, Telegram, Discord.
So it solves some problems.
The silver bullet for me: "only losers do not finish work they started." - Think and grow rich book.
The main key: Persistence. "I will finish it even if I have to fail it thousands times".
A rich guy shared it with me.
As a man, who've building a product for 6 years, I understand you well.
Keep pushing yourself. As @Shindi said, it is important to start from potential customers and their needs first.
How many queries in realities do you need to fetch all “page” data?