"Don't let social media fool you, the average millionaire is 50+ not 19"

But who wants to be average

Someone in their 20s who is:

- Delusionally optimistic
- Obsessed with their goals
- Moving with real urgency
- Productive, not just busy
- Seeing patterns early

That person is going to end up somewhere almost nobody else reaches. not because of luck. because they refused to move at the speed everyone told them was reasonable.

At this point, Inflation is just Theft.

Netanyahu is flying to Washington, DC on Saturday night July 18th and staying until Tuesday.

Netanyahu visited Trump on Mon Dec 29, 2025, the Venezuela invasion began 1:30am Sat Jan 3, 2026

💥 IRAN WAR - THE MOVIE💥

AI has to be the greatest #PSYOP in history.

They've convinced the public to "invest" (fund) the construction of their own surveillance state. #PSYWAR

So with Stripe buying PayPal, does that mean Elon now owns what he created in 2000?

Musk is a seed investor of Stripe and X uses Stripe for their financial services.

Loop engineering is the biggest shift in AI prompting we've ever seen.

Pair it with Fable 5, and you'll have AI agents working for you while you sleep, building anything you could think of.

Every good loop has six working parts:

1. Trigger (Automations)

The trigger is what starts the loop.

In Claude Code, you trigger agentic loop automations with /schedule and /loop (more on prompting later).

/loop runs on a specified interval; without an interval, it self-paces based on output.

2. Execution Layer

This is where Claude actually does the work.

It reads the current state, takes action, and produces outputs.

No manual input is needed - just watch Claude work.

3. The Verifier

This is where you give Claude a checkpoint.

Things like: Tests, a build, a screenshot to compare.

Using a verification layer helps ensure Claude is actually on the right track and not producing slop.

You can use the /goal command, which takes things a step further by running a separate fast model to grade the work after every turn.

4. Stop Rules

Every loop needs two types of stop conditions:

Success stopping (all tests pass, task complete)

Failure stopping (retry count exceeded, unrecoverable error).

You can also add stop rules, such as a token budget, which can help manage AI spend.

Make these explicit in your instructions, not implicit:

You have a maximum of 20 attempts. If all tests pass, report "TASK_COMPLETE" and stop.

If you encounter an error you cannot resolve after 3 retries, report "TASK_FAILED: [reason]" and stop.

5. Memory (Progress File)

Keeping a markdown file of Claude's progress is generally good practice.

A simple log of what's been done so you can check its work and go back if needed.

6. Skills (CLAUDE.md)

Skills are saved instruction sets that freeze project knowledge so the agent doesn't re-learn the same context every session.

Your CLAUDE.md file is what gives the loop its personality and sets its constraints for every run.

Tip: Keep it short. A bloated rules file gets paid for on every single beat of the loop.

Put all six together, and the optimal loop structure looks like this:
TRIGGER → every 15min / on PR comment / on CI failure
DOER → Claude works the task
CHECKER → separate model grades the output
STOP → all tests green, or 10 iterations, or $5 spent
MEMORY → progress.md updated each run
SKILLS → CLAUDE.md read on every session start

AND NOW THEY FIND OUT!!!😎🇺🇸💥💥💥

Ships transiting Hormuz fell from 540 a week to 67. Cargo capacity fell from 20.2 million metric tonnes a week to 2.2 million.

That is an 88% collapse in traffic and an 89% collapse in cargo capacity since February 27, sustained for over 4 months now.

Probably one of my favorite quotes from Bezos

Business sometimes presents you with opportunities where the risk return curve is so skewed that it would be a mistake to not take a massive swing

Even if you miss 9 out of the 10 shots, one big winner pays for all the failures

I like to imagine a future where the CIA sits on the fact they invented #Bitcoin until one BTC is worth 100M, at which point they sell Satoshi’s stash ($110T) to clear out the national debt and cement their place in history as the greatest deep state known to man

When your coworker is max long software

Bullshit

The good people won and evil was defeated today 😂😂😂

POV: You finally realise you work 15 years for FREE in a 40 year career due to taxes

They got us by the balls