nightwolfx2

OSCE3 | OSED | OSEP | OSWE | CRTE | OSWP | OSCP | GWAPT | RMHT ❤️

[rari @0xwhrrari]

Anthropic hired this engineer at $250K-$750K a year because he knows how to build harnesses for multi-agent systems

In this 15-minute workshop, he shows exactly how to build one from scratch

AI → Agents → Harness → Loops → Graphs

step 1 → start with the Claude Agent SDK - the harness handles loops, context, and sandboxing

step 2 → separate the brain from the hands - reasoning in one place, tools in a sandbox, 60% faster to first token

step 3 → run it server-side and log every step - close your laptop and it keeps running, crashes resume from the log

step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over

step 5 → turn yesterday's logs into new memory and skills - the harness wakes up smarter

Anthropic calls this "dreaming"

Most people spend weeks building this by hand

You don't have to

Bookmark and watch it

Then read the full harness engineering guide below ↓

[reira @reiraxbt]

Andrej Karpathy spent 8 years at OpenAI and Tesla

Last week, he compressed everything he knows into one free 2-hour lecture

Agents → Loops → Harness → Self-Improving Systems

People spend $15K on bootcamps that teach less than this

This lecture beats most paid AI engineering courses

You probably don't have 2 hours right now

Don't let this vanish from your feed

Watch it

Then read the article below

[Vivi @vivistac]

Anthropic ha lanzado una guía de 37 minutos para construir Agentes de IA que automatizan una empresa entera.

Gratis. De los ingenieros que construyeron Claude.

Agentes que trabajan, se reparten tareas y ejecutan todo solos.

Subtitulado al español.

Guárdate este post. 🔖

[Khairallah AL-Awady @eng_khairallah1]

this is f*cking gold

How to build your first AI agent (Full guide)

if I had this a year ago, I would've shipped my first app in a day instead of 2 weeks

in the right hands, this changes everything:

[Swati Gupta @hrswatigupta]

Instead of watching an hour of Netflix, watch this 2-hour Stanford lecture, which will teach you more about how LLMs like ChatGPT and Claude are built than most people working at top AI companies learn in their entire careers.

[Raytar @Raytar]

Anthropic engineer:

"At Anthropic, we don’t write prompts anymore. We build loops."

In 45 minutes she shows how the Claude team builds loops that prompt themselves.

If this cost $300, people would call it the best agents course of the year. It's free.

Watch it, then build your first loop with the step-by-step guide below.

[rari @0xwhrrari]

Anthropic just released a free 4-hour course

On using Claude with the same workflows as their own engineers

00:15 - How to prompt Claude the right way
11:41 - The output contract that fixes inconsistent answers
30:04 - The loop that makes Claude agents more reliable
33:21 - Why Claude struggles with coding tasks
01:33:39 - The workflow Anthropic engineers use every day
02:50:56 - The simple tweak that makes Claude much smarter

These 4 hours are better than any paid vibe coding course

Bookmark and watch it today

Then read the article below

[Precis0x @precisox]

Ex google engineer acaba de soltar un curso completo de 1 hora para construir agentes de IA que se mejoran solos, desde cero:

00:00 – Cómo nace un agente que se construye a sí mismo
03:01 – soul.md: el archivo que lo controla todo
30:16 – RAG inteligente: solo traes 20 mensajes relevantes, no los 2.000
31:48 – El loop que sabe cuándo parar solo
35:14 – Detectar el error y arreglar el prompt en el momento
50:22 – Cómo Claude comprime y optimiza tu memoria automáticamente

1 hora de contenido práctico que vale más que la mayoría de cursos de pago sobre agentes.

Míralo completo, guárdalo📚

[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.

[Codez @0xCodez]

Anthropic just released 5 workshops on building self-improving agentic systems from scratch:

00:00 - Ship your first Claude agent
36:44 - Self-improving agents (tools,skills)
1:21:25 - Build memory for Claude agents
1:49:47 - Set up a proactive agent
2:11:31 - Make your agent autonomous

These 3-hours of Claude workshops will replace 20 paid agentic courses.

Watch today, then read article below on how to build a self-improving agentic system with Fable 5.

[Rohit @heyrohitai]

🚨 Anthropic just showed a 24-minute workshop on how to actually do prompts for Claude.

Taught by the people who built it.

Free. No registration. No paywall.

I've seen $300 courses that don't cover what they teach in the first 8 minutes.

Watch it and bookmark it now.

[Nicolas Krassas @Dinosn]

0liverflow/cve2poc: CVE2PoC is a tool that helps penetration testers, bug hunters, and security researchers quickly find public exploits or PoCs related to a CVE ID https://t.co/ggJxFLaMae

[Nicolas Krassas @Dinosn]

poellie01/pentestcompanion: The ultimate pentesting companion. Keep all your pentesting artifacts in one place. https://t.co/4dp68ryKR9

[Anuj @anujcodes_21]

🚨Anthropic just showed a 24-minute workshop on how to actually do prompts for Claude.

Taught by the people who built it.

Free. No registration. No paywall.

I've seen $300 courses that don't cover what they teach in the first 8 minutes.

Watch it and bookmark it now.

[Ignacio Gómez Villaseñor @ivillasenor]

Es muy triste que la @SEP_mx (en realidad @mario_delgado) le dé prioridad a tener calles vacías para los turistas por el Mundial y saque a los niños de las aulas justo cuando hay una caída en la educación.

Nunca quedó mejor la frase «pan y circo para el pueblo».

[Matt Johansen @mattjay]

He began by replicating Mythos findings with his specialized harness.

Then went on to find more critical novel zero days in open source code that he can't share yet because they're not fixed.

TL;DR - harnesses are where the magic is. https://t.co/e8jhbktBKQ

[nightwolfx2 @nightwolfx2]

@DeadSector He got promoted to the God level now

[网安知识分享 @cybersecuritysl]

Free. Open source.

[Abdelrhman Amin @0xUchihamrx]

Hello all,
I'm excited to share my recent bug bounty write-up

How I found 2 critical vulnerabilities in a desktop app exposing internal systems & user PII.

Full Story: https://t.co/1qCYqfnqGn

#bugbounty #bugbountytips

[Het Mehta @hetmehtaa]

LLMs for vulnerability research by @0xAsm0d3us

https://t.co/GLaabD7Ahi