wook kim

[Miles Deutscher @milesdeutscher]

Anthropic's internal loop engineering playbook just got leaked.

And it's the most valuable AI guide I've read all year.

This guide is packed with info, and there are five things you need to know if you want to maximize your AI productivity with loops (save this):

1. You should structure every loop around these 5 principles:

• Discovery → Let the agent find its own work (CI fails, issues, commits)
• Handoff → Give every task its own isolated git worktree
• Verification → Never let the generator grade its own work
• Persistence → Always write state to disk (markdown or board)
• Scheduling → Run it on a timer so it works while you sleep

2. Separate Generator from Evaluator (most important rule)

Use two agents: one writes, the other is a skeptical judge who assumes the code is broken.

Make the evaluator act (run tests, click buttons, take screenshots) - this is what actually stops bad output.

3. Build with these 6 parts:

• Automations (the timer)
• Worktrees (safe parallelism)
• Skills (permanent project knowledge)
• Connectors (talk to GitHub, Linear, etc.)
• Sub-agents (generator + evaluator)
• Memory (state files that survive between runs)

4. Things you must watch out for with loop engineering:

• Verification debt (use verification agents)
• Losing understanding of your own codebase (start fresh if needed)
• Token costs exploding (solution below)
• Cognitive surrender (don't stop thinking because “the loop handles it”)

5. Solving token costs

Loop engineering can be crazy expensive.

I recommend you use an 80/20 "barbell" approach to loop engineering.

For your most complex tasks that require the best intelligence, use expensive models (Opus).

For the remaining 80% of your tasks (the gruntwork), use cheap, open-source models within the Claude Code harness (GLM-5.2 is great for code execution).

Save these 5 rules so you don't forget them.

[peptidedaily @peptidedaily_]

This doctor has treated 100,000+ patients with peptides, with almost no side effects.

After watching his full interview with Gary Brecka, I pulled out his 7 wildest takes that will change the way you see peptides:

(1/7) Peptides > Aderall

[Hamza Khalid @humzaakhalid]

How much YouTube pays you to start a faceless YouTube channel

1,000 views = $8
10,000 views = $70
100,000 views = $700
1,000,000 views = $7,000
10,000,000 views = $70,000
100,000,000 views = $600,000

Here's how to do it using Claude:↓

[Roan @RohOnChain]

this is f*cking dangerous

6-page pdf along with CODE to build a hedge fund using "loop engineering" that prints alpha 24/7

bookmark & feed this paper into claude code before someone takes it down, thank me later

[Chase @0xChaseTM]

A $3,000 3D WEBSITE STARTED WITH A SINGLE CLAUDE PROMPT

The prompt was short. The result wasn't. Claude turned a single request into a 3D site with a spinning product, smooth animations, the polish you'd expect from a paid studio

He didn't hire anyone. He didn't open a design tool. He just asked, and it got built

Think about who used to be able to do this. You needed a team, a budget, and weeks of work. Now it fits in one sentence and a few minutes of waiting

The crazy part isn't the site. It's that the same result is sitting one prompt away for anyone willing to ask for it

He just got there first. Claude did the rest

[William Makis @MakisMedicine]

IVERMECTIN for 10 cents

It really doesn't take very long to find. 😃

This one took about 5 seconds of searching on IndiaMART:

Supreme Pharmaceuticals in Maharashtra is rated 4.6/5 with 540 reviews, and ships to USA, UK, Saudi Arabia, Australia and Tanzania

8.6 cents per Ivermectin 12mg

https://t.co/CLimPRVGiX

Or another one:

Nikhil pharmacy, rated 4.8/5 with 186 reviews and ships to USA, Canada, Australia, UK and France

9.7 cents per Ivermectin 12mg

There are hundreds of options, and IndiaMART is a platform like Amazon or Ebay.

https://t.co/jVcJiA8mhr

[Rahul @sairahul1]

Sam Altman:

"We're going to see 10-person billion-dollar companies pretty soon."

"If I were 22 right now, I'd feel like the luckiest kid in history."

Most people will read this, feel inspired for 3 minutes, and go back to what they were doing.

The ones who act will build a one-person company this weekend.

One tool. Claude Cowork. Full operation.

This is the exact playbook ↓

[Roan @RohOnChain]

"I told Claude 'remember you are not human' and it started working 10x better."

"I have not written a single line of code in 14 months. I just run loops that write code for me."

1 hour masterclass on loop engineering that will turn you into the most dangerous person in AI right now.

You will level up your coding and ship 10x faster.

If I had this a year ago, I would've built my self improving hedge fund in a week instead of a year.

Bookmark this, then read the article on building hedge fund.

[Kirill @kirillk_web3]

me seeing Claude users run automated YouTube systems

pulling $10k, $50k, $100k months while I'm still writing prompts by hand

and someone dropped a full guide on how they do it

my reaction:

[wook kim @wookmon]

https://t.co/PsXPPMV3II

[Movez @0xMovez]

A senior Google engineer just dropped a 19-page PDF on "Loop Engineering" for LLM and agentic systems.

Act → Observe → Learn → Repeat

• Act: the LLM proposes a code transformation (tile this loop, parallelize that one).

• Observe: a compiler runs it and reports back - is it valid? faster? slower? by how much?

• Learn: the LLM reads that feedback and adjusts its next move.

• Repeat until it stops finding improvements.

The agent gets smarter purely from grounded feedback inside its own context window.

This 19-page PDF totally changed the way I’m building agentic systems today.

Read it now, then explore the article below.

[Codez @0xCodez]

A senior Anthropic engineer just dropped 11-page PDF on "Loop Engineering" for agentic systems.

The shift: you stop prompting the agent. You build the system that prompts it instead.

Schedule → Discover → Build → Verify → Repeat

Every loop runs one turn, five moves:

• Discovery: it finds its own work - failing CI, open issues, recent commits - instead of being handed a list.

• Handoff: each task gets an isolated git worktree so parallel agents don't collide.

• Verification: a second agent, told to assume the code is broken, reviews the first. The "thing that can say no."

• Persistence: results get written to disk, never left in a context window that gets flushed.

• Scheduling: an automation wakes it on a timer. That's what makes it a loop.

The key insight: an agent grading its own work always praises it.

This 11-page PDF changed how I'm building agentic systems today.

Read it now, then explore the article below.

[Roan @RohOnChain]

this is f*cking dangerous

someone just open sourced the entire "LOOP ENGINEERING" framework for free

build a hedge fund printing alpha 24/7 by feeding it into claude code with my article below

bookmark before someone takes it down

[Kirill @kirillk_web3]

Cut Your Claude Code Token Usage by 90%

He leaked the exact methods. Most people will scroll past it.

Nothing complicated.

Bookmark this so you don't lose it.

[Healthy Alfred 🌴🥥 @HealthyAlfred]

BPC-157 healed every tissue scientists tested it on. every. single. one.

nerves. tendons. bone. liver. gut. eyes. heart. brain.

30 years of testing. zero failures.

sounds impossible right? I thought so too. then I tried it.

→ severed nerves — REGREW
→ Achilles tendon — REATTACHED
→ torn ligaments — REBUILT
→ bone defects — CLOSED
→ punctured cornea — SEALED
→ destroyed liver — REVERSED
→ shredded gut — REPAIRED
→ stopped heart — RESTORED
→ Parkinson’s — REVERSED
→ crushed spinal cord — RECOVERY at 360 days

ZERO lethal dose. ZERO cancer cases. ZERO toxic reactions.

Huberman — years of back pain. gone.

Rogan — elbow tendonitis. gone in two weeks.

RFK Jr. — “big fan.” FDA now reclassifying it.

still waking up in pain? still avoiding the gym? still popping painkillers?

that’s not aging.

that’s a repair your body started and never finished.

BPC-157 restarts it.

your doctor has never heard of it.

your stomach has been making it your entire life.

would you believe me now?

🧵 everything it healed, how I take it, and proof from others below ↓

[Avid @Av1dlive]

Spacex just bought Cursor for $60 billion.

the same day, Kevin Niparko ( Product Lead at Cursor) showed exactly what Elon bet on:

"we're moving towards an era of loops and agent systems

where agents are going to continue to be working on our behalf at all times"

13 minutes that laid out the next five years of how software gets built: agent swarms + loops.

i wrote the full guide on building agent swarms two weeks ago.

bookmark it before you need it.

[Roan @RohOnChain]

this is f*cking dangerous

build hedge fund using "loop engineering" that prints alpha 24/7 (Full Guide)

if I had this a year ago, I would've built my hedge fund in a week instead of a year

bookmark before someone takes it down

[Noisy @noisyb0y1]

APPLE JUST SHOWED HOW TO RUN 10 AI AGENTS LOCALLY ON MAC - NO CLOUD, NO API KEYS, ZERO COSTS

00:10 Apple engineer says: "your data stays on your device, AI available anywhere at any time, zero usage costs"

agent reads your code, checks GitHub, finds what needs attention and writes a report - all on your Mac, nothing goes to the internet

10 agents work simultaneously - one writes code, another tests, third fixes bugs - parallel with no queue

built a full iPad app from scratch in 2 minutes, fixed its own mistakes and compiled without issues

takes 5 minutes to set up - and you never pay again for a bot that runs 24/7

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineers just showed how they build a full app from scratch, using a loop of agents

40 minutes from the team behind Claude Code

they used three agents: one to plan, one to build, one to judge, cycling until the app actually works

the winners won't have the smartest model, they'll have the best loop

watch it, then read the full guide on how to actually use loops below

[Elon Musk @elonmusk]

Good idea