Most people quit because they forget that you have to be bad at something before you can be good at it. It's so obvious. You suck. Of course you're not going to win in 2 weeks. But if you can learn to enjoy extended periods of failure, you will make it very, very far in life.
“All the good ideas are taken.”
“If I was born 5 years earlier I’d be rich.”
“I missed the window.”
People said this about dot-com, Web 2.0, social, mobile, cloud… and now AI. There’s always another window. The people who aren't complaining are the ones who are seizing it.
The funniest take is that I "failed" 43 times when people look at my GitHub repos and projects.
Uhmm... no? Most of these are part of @openclaw, I had to build an army to make it useful. https://t.co/GLR35USlzu
applying to jobs is the dumbest shit you can ever do.
i learned the hard way. dmed a 1000 recruiters/engineers. did 670 apps. didn't get me anything.
cause its not equally distributed: the top 10% of people take 90% of the jobs.
it's the same everywhere else. the hottest girl gets 90% of the guys. the largest artist gets 90% of the streams.
so this past year i stopped wasting time on applying and started doing whatever gave me the biggest impact. did hella trips to sf/nyc, built products, did content, made friends.
and soon the dynamic flipped. jan-may, 83 recruiters dmed me. ai labs, yc companies, unicorns.
it's a winner-takes-all world. you have no choice but to become the winner. or waste away your life fighting for scraps.
Opportunities always favor the people who try first!
I still remember when Bhanu first started working on https://t.co/YQ7cOmf13e. Back then, Notion was just taking off. Later, he sold Feather for $250k.
Then ChatGPT exploded. He was among the very first to build AI chatbots, and now https://t.co/HwfRWFE7qU has reached $100k+ ARR.
Now OpenClaw is blowing up. Again, he’s one of the earliest to try monetizing this open source project. In just a few days, the project has probably already crossed $100k ARR.
And btw, this guy is from India. When I talked to him before, he told me their village had frequent power outages.
Seriously, if you truly have passion for what you’re building, everything else is just noise. You really don’t need to be in Silicon Valley.
my favorite way to use Claude Code to build large features is spec based
start with a minimal spec or prompt and ask Claude to interview you using the AskUserQuestionTool
then make a new session to execute the spec
Highly recommend this blog from cursor: https://t.co/UJnSwAnILV
My takeaway:
1. Choose model by agent role
2. Prompt engineering still very important
I'm feeling agent orchestration will attract more attention in 2026, maybe another "k8s for AI" will appear.