Suresh Naidu

Cloud & Devops Engineer, AWS and Azure lover, sports enthusiast, movie lover… #ONE-EARTH - SAVE THE EARTH

[Suryansh Tiwari @Suryanshti777]

Anthropic's Claude Code team just broke down how they actually think about agent loops.

Not one loop — four. Turn-based, goal-based (`/goal`), time-based (`/loop`, `/schedule`), and proactive, which runs on its own with zero human in the room.

Most people are still manually re-prompting Claude one turn at a time, treating every task like a fresh conversation.

That's the actual gap right now — not who uses AI, but who's still prompting vs. who's running loops.

Bookmark it

[Amarillo @anyelamarillo]

🚨 ¡BOMBA para devs!

Anthropic acaba de soltar un curso 100% GRATIS sobre Loop Engineering con Fable 5 y está rompiéndola.

Este curso reemplaza cualquier tutorial de pago de Claude Code que exista ahora mismo.

Mira lo que te enseñan (con timestamps):

00:00 → Cómo funciona Claude Code por dentro
05:01 → El agentic loop explicado (esto sí que vale oro)
16:21 → La función que el 99 % de los devs ignora
19:01 → Por qué la voz le gana a escribir
32:34 → Revisión automática de código con Draft PRs
58:39 → Fable 5 para trabajo que NO es código

Guárdalo YA. Míralo completo. Y compártelo con quien esté perdiendo tiempo pagando cursos.

El que lo vea entero va a tener ventaja brutal los próximos meses 🔥

[Aria Westcott @AriaWestcott]

An asian guy just found a way to use Fable 5 forever, even though Anthropic is going to make it access-limited after 12th July.

He used Opus 4.8 to host the operating manual of fable 5 with just one single prompt.

Access to the best model is never guaranteed. It disappeared once already this year.

But you can use it forever. Here's how:

1. Extract the operating manual of Fable 5
2. Create an .md file and save it on your device
3. Create a new project "Fable 5 Brain" in Claude
4. Paste the instructions/ .md file straight into it
5. Run a pressure test to verify

Save and bookmark this no matter what:

[Lunar @LunarResearcher]

this is f*cking dangerous.

most people are paying Claude Code to forget.

fix bug → lose context → restart → repeat

that’s not agentic coding.

that’s renting the same brain every morning.

LOOPS.md changes the game.

observe → patch → test → verify → record

the loop remembers what the session forgets.

bookmark before Anthropic ships this as "persistent agents."

[Rahul @sairahul1]

Google just dropped a 1-hour course on agentic engineering from scratch:

00:00 – How to build your first AI agent
08:24 – Build agent memory (short, persistent, long)
28:34 – Agentic loops, long-running AI agents
40:04 – How to build MCP (MCP vs API)
1:00:22 – Multi-agentic systems

This 1-hour watch will replace 10 paid agentic courses on the internet.

Bookmark this. Watch this weekend.

[MIKE @mikenevermiss]

THIS GUY USED CLAUDE TO BUILD AN AUTOMATED TRADING SYSTEM THAT GENERATED $847 OVERNIGHT.

it all started with a single article about Polymarket bots.

Claude Fable 5 read it, selected 7 GitHub repositories, connected them into a working pipeline, and deployed the entire system from start to finish.

from there, everything ran autonomously.

the system:

→ scanned 412,000+ trades

→ tracked whale wallets

→ detected insider activity

→ analyzed the market every few seconds

→ decided whether to buy, sell, or pass

→ executed every trade automatically

according to him, the system completed 47 trades and ended the night with $847 in profit, without any manual intervention.

the video below teaches you how to replicate this system yourself, step by step.

[おじぎねこ🐱AI自動集客 x アフィ @ojigineko_tips]

この記事コピペしてClaude Codeにぶん投げればFable 5が勝手に第二の脳を設計してくれるよ
あなたのClaude Codeに最適化された世界に一つの第二の脳が構築される
👇️やるべし！

[Charly Wargnier @DataChaz]

Claude users after reading this:

[The AI Colony @TheAIColony]

https://t.co/YynzlNqIY0

[Robust Feed @RobustFeed]

STOP! You're Probably Doing This Dumbbell Chest Exercise Wrong!

[m0h @exploraX_]

you can build your own AI agent completely FREE using this github repo.

zero cost. no subscription. no API payment. MIT licensed.

all of the stack in this repo is free forever:
— langchain + langgraph (the framework)
— groq or google's gemini free tier (the brain)
— and your laptop.

the article quoted below is the full guide, the tools are open-sourced and you'll find the repo link in the comment.

[Fitness Doctor 🩺 @FitnessDr_]

5-Day Gym Split + Meal Plan for Serious Gains

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineer:

"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."

In 45 minutes she breaks down how Anthropic builds agents that remember, learn from their mistakes, and get smarter with every run.

Worth more than any paid course you'll find on building agents.

Watch the session, then read the guide on building loops below.

[Anatoli Kopadze @AnatoliKopadze]

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.

[Dipanshu Kushwaha @Dipanshu_AI]

Everyone is talking about AI.

Very few understand what's actually changing.

Andrej Karpathy explains it in one sentence:

"We're now programming computers in English."

This isn't just another AI talk.

It's a roadmap for the future of software. 🚀

[Hanako @hanakoxbt]

KARPATHY JUST KILLED THE PROMPT ERA WITH A SINGLE DOCUMENT

prompts are easy. loops are hard. and writing fifty prompts a day is the work nobody does twice.

he shifts the burden to the harness.

you define the contract once. the model writes, reviews, restarts, and reconciles. you keep judgment. it keeps the loop.

the throughline is the same in every rule: the human owns the spec and the boundary. the model owns the execution and the bookkeeping.

planner never touches code. generator never grades itself. state lives on disk, not in context.

9 rules. start with one feature, not ten. most people are still typing prompts. this turns Claude into an agent that finishes the job on its own.

here is the official document from Karpathy explaining the architecture

[GetFIT CENTER @center_getfit]

Effective workout for flat tummy👇save this .

[Mobility Exercises | Pain Relief Workouts @FeelGoodMovez]

Chinese longevity hacks

[MIKE @mikenevermiss]

You’re probably not expecting this.

A developer ran Llama 3.3 70B locally on a MacBook for an entire 11-hour flight.

No internet.
No APIs.
No Claude.
No OpenAI.

Just a fully local AI model running the whole time.

While everyone else was paying for unreliable in-flight Wi-Fi, he had a 70B model running completely offline.

It feels crazy, but this is where AI is heading.

Save this, you’ll want to come back to it.

[NeilXbt @neil_xbt]

https://t.co/aGp0j0VetB