met an anthropic engineer making $1.2M a year.
asked him how he ships alone at the pace of a full team.
he didn't answer. sent me his .claude/. one folder.
SAME MODEL - DIFFERENT RESULT.
everyone's still picking between opus and sonnet like the model is the ceiling. it isn't.
the real lever is what the model wakes up into:
CLAUDE.md → hooks → verifier subagent → skills → mcp → memory → shift notes.
you stop chatting with the model.
you write the folder once. the folder runs the model.
- CLAUDE.md - the contract
- settings.json - the permissions
- hooks/ - the reflexes
- agents/verifier - the shift-notes cop
- skills/ - 33 muscle memories
- .mcp.json - the tools
- MEMORY.md - the shift log
that's the stack.
full breakdown in the article below. bookmark before he realizes i posted it.
يا جماعة، سواء رجال أو نساء، احفظوا هالتمرين وداوموا عليه.
سووه 5 أيام، أو 10 أيام، أو حتى 50 يوم، المهم تستمرون لين تتقنونه بالكامل.
التمرين هذا يشغّل تقريبًا أغلب عضلات الجسم خلال 24 ثانية فقط، ومع الاستمرار بيعطيكم قوة ولياقة بدنية رهيبة، وبتحسون إن جسمكم صار يشتغل كأنه آلة رياضية.
Un amigo mío gana 1,2 millones de dólares al año como ingeniero en Anthropic.
Le pregunté cómo llegó a dominar tan bien el prompting.
Me envió un video que nunca debía hacerse público: el manual interno de prompting del equipo principal de Anthropic.
No vas a encontrar nada mejor sobre prompting que ese video.
Lo vi anoche.
A mitad del video me di cuenta de que llevo dos años usando Claude de la forma equivocada.
Míralo y luego lee el artículo de abajo.
Anthropic engineer:
"You can build 5 assistants in one afternoon. Each one handles a task you've been doing manually every single day."
In 45 minutes he shows exactly how to do it from scratch, step by step.
Most people are still doing all of this by hand.
Watch the session, then save the guide below.
this is f*cking gold
Andrej Karpathy joined Anthropic five weeks ago.
A friend on his team just showed me the exact LOOPS.md file he actually uses.
I dropped it into my setup. The very first response was different.
Not slightly different. Completely different.
Claude stopped giving generic answers and started working exactly the way I think.
You don't talk to the model anymore. You build the system that talks to the model for you.
Bookmark it before it gets lost in your feed.
Read it now, then check the article below.