Hey guys I just left Dodger stadium with 2 other chefs to follow our dream. We have started our own taco stand and catering service called Narcos Tacos. Im having my first event this week and it would mean the world if yall could follow or just simply RT.
-Thank you much love
ANTHROPIC JUST EXPOSED HOW BADLY MOST PEOPLE ARE PROMPTING CLAUDE.
Their applied AI team dropped a 24 minute workshop.
Free.
From the people who wrote the model.
Not a course creator.
Not someone who figured it out by accident.
THE TEAM THAT BUILT THE THING.
Here is what makes this uncomfortable to watch.
There are 6 elements to a properly structured Claude prompt.
Most people are using 1.
Maybe 2 if they are being generous with themselves.
That gap is the difference between Claude giving you something useful and Claude giving you something you could have Googled.
The people who watch this workshop tonight will prompt differently tomorrow morning.
The people who skip it will keep wondering why their outputs feel slightly off no matter how much they tweak the wording.
24 minutes.
Free.
From the only people on earth who know from the inside exactly how Claude thinks.
I watched it twice.
Then I built a Claude Skill that applies all 6 elements automatically so you never have to think about prompt structure again.
Every prompt you run goes through the framework without you doing anything manually.
Full guide and the skill setup is below.
Bookmark this.
Come back to it this weekend.
This is the thing that compounds.
Follow @cyrilXBT for the exact Claude skills, prompt architecture, and systems I use to get outputs that most people do not believe came from one person.
🚨 A junior at Jane Street reportedly landed a $220K–$600K role because he used AI to analyze trillions of data points faster than most teams ever could.
In this 1-hour lecture, he breaks down the exact system behind it:
• how he researches massive datasets
• how AI finds patterns humans miss
• how his machine turns raw data into decisions
• how you can apply the same thinking yourself
Skip Netflix tonight.
Watch this instead.
One hour could completely change how you think about research, AI, and opportunity.
A Meta engineer recognized my screen at a rooftop bar in SoMa
I was checking my Polymarket positions on my laptop. He stopped mid-conversation with his group. Walked over.
"That's not Robinhood. What are you running"
I told him. Claude Code. Four repos. $25 a month.
He pulled up a chair.
"We prototyped something like this on our infra. You let the model analyze raw trade data. It finds its own signals. But legal shut it down before it ever went live"
I asked what signals.
He pointed at my screen.
https://t.co/klxt0tvrOd
86 million trades. Every wallet. Every entry. Every exit.
"You're not giving Claude rules. It's finding the wallets that consistently win. Then it reverse-engineers their timing. Then it copies them"
His team spent 6 months on this. 9 people. Internal GPU cluster.
"The thing we never cracked - when to get out. Entry is easy. Exit is where all the alpha lives"
I told him my bot cuts at 85% of expected move or on a 3x volume spike.
He stopped talking.
"How did you figure that out"
Claude Code found it in poly_data. Top wallets exit before resolution 91% of the time. They capture 86% of the move and walk away. Losers hold to 58%.
He opened his phone. I showed him the second repo.
https://t.co/SbyxXxFk0M
Three commands. 500+ markets. No API key. Claude scores them in 20 minutes.
"That's literally what we built. Except we had 9 engineers and you did it in a weekend with a $25 subscription"
My setup:
Claude API - $20/mo
VPS - $5/mo
poly_data - free
polymarket-cli - free
19 days. 4 agents. 74% win rate.
Copytrade here: https://t.co/N2byLbMfwH
I showed him the full breakdown - every repo, every command, every dollar.
He read through it. Then looked up.
"You just published our internal roadmap"
He messaged me two days later.
"My director found your post. Delete it"
Too late.
CLAUDE MADE ME 3 TRADING BOTS IN 15 MINUTES
+$2,503 in my wallet the next day, I quit my job that same day.
I wrote one prompt and answered a few questions.
Claude took three strategies - MACD, RSI + VWAP, CVD divergence. Assigned each bot its own.
The first one catches momentum - sees when volume picks up and gets in before the crowd wakes up.
The second one trades reversals - waits for everyone to panic and bets against them.
The third one scans divergences - when price says one thing but money does another, it follows the money.
Built the structure itself, wrote the backtest, ran each strategy on historical data, set up the risk manager, deployed - all on its own.
Three bots, three accounts, each trades differently - they don't know about each other.
Started with $1, then $5, then $10, then $50, then $2,503 in a day.
Citadel, Jane Street, Two Sigma have been trading with bots for years - they don't feel fear, greed, or FOMO - they only listen to algorithms.
The market rewards systems.
Eight years ago, Jen-Hsun Huang himself delivered the first AI-focused GPU made by Nvidia to OpenAI.
This event signaled the end of Intel's control in this area.
It wasn't just luck, but something more profound.
Jensen publicly shared that Nvidia succeeds by following four main values: ↓🧵
I am obsessed with learning everything.
So, I spent 100+ hours studying how Elon Musk absorbs information.
He literally taught himself everything about programming, reusable rockets, electric cars, etc.
Here's what I found on how to learn anything:
NEW: 62-year-old Boeing whistleblower John Barnett found dead in his truck after he didn't show up for a legal interview linked to a case against Boeing.
Barnett worked for Boeing for 32 years and retired in 2017. After retiring, Barnett spoke out about how Boeing was cutting corners on their airplanes.
Just days before his death, Barnett gave evidence in a lawsuit against Boeing.
Barnett accused Boeing of "deliberately fitting sub-standard parts" on their aircraft.
He also accused Boeing of having faulty oxygen systems, saying one in four breathing masks would *not* work in an emergency situation.
Barnett said new plane builds were rushed. When he brought his concerns forward, they were allegedly ignored by the company.
When he died, Barnett was in Charleston for interviews linked to a case against Boeing.
He was supposed to come back for more questioning on Saturday but did not show up. Inquiries were made to his hotel where Barnett was found dead in his car in the parking lot.
Police are investigating Barnett's death but say he died from a "self-inflicted" wound.
The video below was a recent interview Barnett had with TMZ.
Totally normal.
“A good book gets better at the second reading. A great book at the third. Any book not worth rereading isn’t worth reading.”, says Nassim Nicholas Taleb.
He is the author of the Incerto, a five-volume philosophical essay on uncertainty.
25 books recommended by @nntaleb 🧵
Sora by OpenAI is insane.
But it doesn't just generate AI videos from text, it can also change the styles and environments of input videos🤯
12 wild examples:
First, Input video 🧵👇
“The Obstacle is the Way by Ryan Holiday”
This book shares with us the collective wisdom of ancient philosophers and greatest thinkers in order to help us accomplish the very specific and increasingly urgent goal we all share: overcoming obstacles.
10 lessons from the book 🧵
I was hyped on the golf simulator business model, but after interviewing an owner I've cooled off.
Here's his story & financials:
- $170k revenue in the first year
- A whopping $350k in startup costs to set up the 4 bays
- Year 1 profit will be $60k
- Gets most business from FB and IG. A huge Black Friday deal brought a ton of customers in the door.
- Their unexpectedly profitable revenue line is club fittings. They take a 20% cut which is around $500.
- Not a ton of work required once memberships are in place, but it takes a ton of effort to acquire customers
- You don't wanna spend too much cash on chipping and putting areas. They come for the simulators.
- Keep an employee there during the day and a key card at night.
- They've had a few broken TVs from golf clubs. Some drunken antics, etc.
I think hosting weekly tournaments and family nights could bring more bodies in the door. Also happy hours, closest to pin prizes, etc.
All in all I feel like there are better opportunities out there for that much upfront cost. Am I wrong?
Follow me @mhp_guy to watch me peel back the small biz curtain.
What exactly is stopping you from:
- Buying durable laser tag supplies online for $5-10k (not Amazon)
- Using Carrd to put up a free website
- Joining all the FB mom groups and posting to FB marketplace
- Charging $250 - $350 for a 90 minute backyard session
- Spend $500 on high quality pictures and some videos for the site
- Target parents with FB ads and optimize your Google My Business profile
In short, what's stopping you from starting a small business that you could fund with a credit card?
It's an asymmetric bet. If it goes well, you're in business. If it doesn't, sell the equipment for a small loss.
Even better, make the website and post the ads before you buy the equipment to test demand.
You don't need an arena or a facility. People pay for this in their backyards for parties.
Does this work? Yes. My friend started this biz in Phoenix. He's netting $3k/month on the weekends, still working his FT job.
His costs are $650/month. Insurance, gas, etc.
Life changing money? No. Life changing first taste of entrepreneurship. YES.
If your pride is stopping you, then you either aren't broke enough or don't want to own a business that badly.
If your know-how is stopping you then re-read everything above and go watch a few YT videos.
The opportunities are all around us.
Follow me @mhp_guy if you either want to feel motivated to start something or guilty for not starting something.
Business plans don't need to be 300 pages. 300 words works, too.
25 Qualities of a Great CEO:
1. Clear thinking
2. Knows the numbers
3. Emotional intelligence
4. Has strong work ethic
5. Positive attitude
6. Honesty and integrity
7. Communicate openly with people
8. Inspire your community
9. Data-driven
10. Know when to ask for help
11. Passionate about your mission
12. Big vision
13. Grit and courage
14. Decision velocity
15. Vulnerability
16. Track record for high performance
17. No ego
18. Curiosity
19. Embrace obstacles
20. Say thanks
21. Radical candour
22. Effective delegation
23. Problem-solver
24. Great coach
25. Gives credit
“Reading an hour a day is only 4% of your day. But that 4% will put you at the top of your field within 10 years. Find the time.”, says Patrick Bet-David.
Reading changed my life when I started reading books and I never stopped.
25 books recommended by @patrickbetdavid 🧵
Why does our world look the way it does?
Because of the most influential design school in history: the Bauhaus.
From fonts to furniture, this is how Bauhaus created the aesthetic of the modern world...