Confession: I’ve been using Claude Code to write all my code for me. And I think it’s making me worse at the thing I’ve loved doing for twelve years.

I can clearly see how AI coding is rewiring our brains – it makes developers crave instant gratification instead of deep understanding, and reduces us to gamblers who pull levers for the next hit of working code.

If this is happening to me, someone who learned to code in the pre-AI era, what’s it doing to junior developers who’ve never known anything else?

A mindset shift that changed the way I think about the world

In India, knowledge is currency. Three months ago, if another founder asked me about my marketing strategy, I’d give them some generic answer and change the subject. You don’t share knowledge until there’s something in it for you.

I recently moved to San Francisco. A CTO of a unicorn startup had read one of my blog articles and we started talking over DMs. When I got to SF, I asked him to meet, and he agreed.

We met in FiDi for a casual lunch. This guy runs the entire company, and he was treating me — a new founder — like an equal. He was openly sharing his experiences, his journey, and his insights. When we were leaving, he offered to help with connections, fundraising, whatever I need.

He gave me a full hour of his day, just to shoot the breeze like two developers do.

This was nothing like what I was used to. Back in India, a person with even a 100-person office would have an air of arrogance. They’d guard their knowledge and time, only sharing when there was a clear benefit to them.

It was that day that I understood the beautiful “infinite sum game” being played in SF.

Some months ago, I visited New York and joined the Recurse Center.

This is after being in San Francisco for a month, staying next to the Embarcadero and attending On Deck Founders.

I’m living in Downtown Brooklyn now, fortunate to find a place that’s just a five minute walk away from the Recurse Center.

It’s been a pleasure to stay in both the cities. Some differences:

The most successful startup I’ve worked with shipped their MVP in 6 weeks.

The least successful one spent 4 months writing specs for a product that never launched.

Here’s what I’ve learned after helping dozens of teams transition from traditional planning to AI-powered development: writing-first culture made sense when building was expensive and slow. Now it’s just bureaucracy.

I celebrate another revolution around the great big ball of fire today. This was a big year for me: I founded my first product startup, all solo.

I’m doing something really hard but I realize I’ve never written down my guiding principles about why I do this. This article is mostly a reminder for me: on what it takes to achieve greatness.

Here’s what I’ve learned so far:

Show Original

Show Stylized

Every developer I know has the same frustrating ritual. Open Claude Code or Cursor and ask it to do a task. The AI gives you generic code, sometimes useful (but usually not). You correct it. It apologizes. You explain again, with additional context.

Rinse, repeat, until you want to throw your laptop out the window.

David Cramer from Sentry recently shared his AI workflow where he maintains manual rules files to give LLMs context. Solid approach, but it feels like too much copy-pasting. It’s 2025, and machines can do a better job of remembering things.

It’s funny how we’ve built the most powerful reasoning systems in human history, then lobotomized them by making them forget everything after each conversation. My question: is there a better way?

This is part of my “AI in SF” series, where I share real AI engineering workflows from San Francisco startups. I recently interviewed engineers from Parabola (they’re hiring btw, more on that at the end). Here’s a technique to teach AI to learn from your mistakes.

You know that feeling when you leave the same code review comment for the third time this month? “Hey, we use relative imports here, not absolute ones.” Or “Remember to handle both null and empty string cases.” Or “This should use our ORM helper, not raw SQL.”

Your team agrees it’s important. People follow it for some time. But three weeks later, nothing’s changed, and you’re still leaving the same comments.

I recently interviewed C.J. and Zach from Parabola (a Series B data automation company) about how they use AI in their engineering workflow. They shared a simple approach that’s replaced most of their linter rules: teaching Cursor to remember code review feedback permanently.