July 20, 2025

“I call these three steps the Million Dollar Weekend process: 1. > Find a problem people are having that you can solve. 2. > Craft an irresistible solution whose million-dollar-plus potential is backed by simple market research. 3. > Spend NO MONEY to quickly validate whether your idea is the real deal (or not) by preselling it”

5:36 PM

“Take me and any of the super-successful entrepreneurs and side-hustle champions I’ve met over the years. It’s uncanny, but the one commonality nearly all of us share is the crazy number of seemingly random things we’ve tried to launch—stretching back to our childhoods. Online courses, self-published books, consulting, Airbnbs, affiliate marketing, YouTube channels, a college dating site, and many more . . . And for all of us, almost all of these projects failed!”

5:36 PM

“but the days when we weren’t afraid to leap into the mud and dirty up our hands were when we learned the fastest (and had the most fun!).”

5:36 PM

“> Most people never pick up the phone, most people never ask. And that’s what separates, sometimes, the people that do things from the people that just dream about them. You gotta act. And you gotta be willing to fail. > —Steve Jobs”

5:36 PM

“personal favorite way to approach starting a business is to have fun!”

5:36 PM

“**Ask Claude to write code that passes the tests**, instructing it not to modify the tests. Tell Claude to keep going until all tests pass. It will usually take a few iterations for Claude to write code, run the tests, adjust the code, and run the tests again. 1. At this stage, it can help to ask it to verify with independent subagents that the implementation isn’t overfitting to the tests”

5:36 PM

“At this stage, it can help to ask it to verify with independent subagents that the implementation isn’t overfitting to the tests”

5:36 PM

“**Ask Claude to commit the code** once you’re satisfied with the changes.”

5:36 PM

“Claude performs best when it has a clear target to iterate against—a visual mock, a test case, or another kind of output. By providing expected outputs like tests, Claude can make changes, evaluate results, and incrementally improve until it succeeds.”

5:36 PM