Antonio Acevedo

Teleco startupeando, la posibilidad de realizar un sueño es lo que hace la vida interesante ;)

[codila @0xCodila]

Google just released free 2-hour course on full Graph engineering: 1 prompt → 100 agents → loops → graphs from 0% to 100%:

10% → 17:44 - build your first agent
30% → 39:30 - Loop engineering: iterate, check, break
60% → 1:12:38 - Graph engineering
75% → 1:34:26 - agents that throttle themselves
100% → 1:55:05 - full graph for multi-agentic systems

everyone builds one agent and calls it done - this is the full system where agents wire themselves into a graph

watch the course, build the graph - then read the full architecture below ↓

[Nix0n @UnTalNixon_exe]

EL MODELO MÁS GRANDE DEL MUNDO OPEN SOURCE CORRE EN MENOS DE 4GB DE VRAM

2.8 billones de parámetros.
GPU de 4GB.
Sin cuantización. Sin destilación. Sin pruning.

Cómo lo hace:
Solo carga una capa a la vez en la GPU.
En los modelos MoE (como Kimi K3) solo carga los expertos que el token necesita.

Resultados:
• Llama 70B → 4GB
• Llama 405B → 8GB
• DeepSeek-V3 (671B) → 12GB
• Kimi K3 (2.8T) → <4GB

Se llama AirLLM.
Open source. 24.5k estrellas.

La mayoría sigue creyendo que necesita una H100.
pero ya no.

Repoo 👇

[I Meme Therefore I Am 🇺🇸 @ImMeme0]

Spain’s Sánchez: “It’s impossible to close the borders.”

Poland: Already did.

Two policies. One works.

Be Like Poland!

[Swati Gupta @hrswatigupta]

ANTHROPIC ENGINEER:

"DON'T PROMPT CLAUDE. BUILD A SYSTEM THAT PROMPTS ITSELF."

In this free workshop, he explains why most people use Claude the wrong way.

And how to turn one AI into an entire team of AI agents.

He covers:

• Proper CLAUDE.md setup
• Plugins almost nobody uses
• Advanced prompt caching (95% cache hit rate)
• Why starting every chat from scratch is a mistake
Worth more than most paid Claude courses.
Watch this and bookmark it.

[Anatoli Kopadze @AnatoliKopadze]

Head of Claude Code:

"85% of our engineers are running dozens or hundreds of agents. The way you do it is graph engineering."

In 40 minutes he explains how a single engineer now does the work of a whole team, how far this has gone inside Anthropic and where it goes next.

This is something you can't skip if you don't want to be left behind.

Watch it, then read the full guide on graph engineering below.

[Sprytix @Sprytixl]

ANTHROPIC'S LEAD ENGINEER WON A $1.2M BONUS FOR A SYSTEM THAT TURNS ANY DATA CHAOS INTO A GRAPH IN 8 STEPS

raw chaos in - self-updating graph out - and the agent gets +42% productivity from day one

Load → Extract → Graph → Index → Query → Memory → Swarm → Update

eight steps, one pipeline, graph grows while you sleep

documents, code, Slack - everything into one stream through Claude Code - nothing gets lost

Fable 5 + Opus 5 extracts entity relationships - Neo4j builds a live structure - zero duplicates

three types of search in one answer - vectors, keywords and graph - merged ranking gives accuracy no RAG delivers alone

a nightly agent pulls new data and updates the graph automatically - the system gets smarter while you sleep

bookmark and paste into Claude Code - a $1.2M system now free

[Gyomei @Gyome1_]

https://t.co/XZPxfRnaCv

[Precis0x @precisox]

Un desarrollador solo ganó el hackathon de Anthropic construyendo ECC (Everything Claude Code), un sistema brutal de agentes IA, en tan solo 8 horas usando Claude Code.

Se llevó $15.000 y lo open-sourceó al instante.

ECC trae:
- Entre 38 y 63 agentes especializados
- 156-249 skills
- 72 slash commands
- AgentShield con 1.282 tests de seguridad
- Aprendizaje continuo en 12 ecosistemas de lenguajes

El repositorio explotó y ya supera los 150.000 stars en GitHub.

Esto ya no es futuro. Es la prueba de que un solo dev hoy puede crear lo que antes requería un equipo entero.

La era del “one person unicorn” ya empezó.

Enlace en los comentarios 👇

[gus @igus_ai]

Un desarrollador acaba de ganar el hackathon de Anthropic.

Creó un producto funcional en 8 horas con Claude Code y se llevó $15,000.

Después lo hizo open source.
Ya tiene 153,000 estrellas en GitHub.

Lo que incluye:

→ 38 agentes especializados (planificador, revisor de seguridad, debugger, code reviewer)
→ 156 skills que se cargan bajo demanda (/plan, /tdd, /security-scan, /quality-gate)
→ 72 comandos slash personalizados
→ AgentShield: 1,282 tests de seguridad en archivos CLAUDE.md, configs MCP, hooks y skills
→ 3 agentes Opus 4.6 corriendo pipelines de red-team (Attacker, Defender, Auditor)
→ Capa de aprendizaje continuo que acumula confianza entre sesiones
→ Cobertura en 12 ecosistemas de lenguajes

Esto es lo que pasa cuando tratas Claude Code como infraestructura y no como un chatbot.

Enlace abajo 👇

[AYi @AYi_AInotes]

Damn，这个必须卧槽一下了，Karpathy 的 CLAUDE.md 只有 65 行，
居然能把 AI 编程准确率从 65% 拉到 94%，

以22 万星标登顶 GitHub 趋势榜，而且绝大多数开发者还没读过，

里面没有一行奇技淫巧，4 条规则全是同一个方向：

→ 先想清楚再写代码
陈述假设，不确定就问，杜绝猜测

→ 从最简方案入手
只写能解决问题的最少代码，不加任何多余抽象

→ 像手术一样精准修改
不碰与需求无关的代码，每行改动都对应明确要求

→ 以目标驱动执行
写第一行代码前，把模糊指令转化为可验证的成功标准

65 行，4 条规则，每一条都在对抗开发者“先写再说”的本能，

本质上是把慢下来这件事变成硬规则，

趁别人还没保存，赶紧先存好 👇

[Nico @nicos_ai]

GITHUB ACABA DE LANZAR LA CERTIFICACIÓN OFICIAL DE UNO DE LOS ROLES TECH MÁS IMPORTANTES DE 2026

→ Agentic AI Developer (GH-600)

Y es la primera vez que trabajar con agentes de IA se convierte oficialmente en una disciplina reconocida de ingeniería.

Ya no hablamos de:
• prompt engineering
• vibe coding
• automatizaciones simples

Hablamos de un nuevo perfil técnico:

→ Agentic AI Developer

La persona que:
• coordina agentes de IA
• construye workflows autónomos
• integra agentes en entornos reales
• supervisa fallos en producción
• evita errores críticos en pipelines CI/CD
• sabe cuándo un agente no es fiable

Antes:
→ “Trabajo con agentes de IA” era difícil de validar.

Ahora:
→ GitHub certifica oficialmente ese skillset.

Y eso cambia el mercado.

Las empresas van a necesitar este perfil.
Pero todavía hay muy pocos developers especializados en ello.

Si ya trabajas con:
• Copilot
• Codex
• Claude Code
• workflows agentic
• automatizaciones con IA

Probablemente ya estés haciendo este trabajo.

GH-600 es la forma de demostrarlo.

Guárdate esto 🔖

[Data Science Dojo @DataScienceDojo]

MCP and A2A are both agent protocols but they operate at completely different layers.

MCP (Model Context Protocol) is about giving one LLM access to external tools. The model stays in the driver's seat throughout: it receives your query, decides which tools to call, gets the results back through an MCP Client, and assembles the final response. The MCP Servers in between are just standardized wrappers around raw APIs — Flight Booking, Google Calendar, whatever you need. One brain. Centralized control.

A2A (Agent-to-Agent Protocol) is about coordination between autonomous agents. There's no single LLM managing everything — instead, an Orchestrator Agent delegates subtasks to specialized agents, each of which has its own tools, its own memory, and its own reasoning loop. The Orchestrator never touches the Flight API directly. It talks to a Flight Agent, which handles that domain entirely on its own, then reports back.

The architectural difference matters when you're building:
MCP works well when one model can reasonably handle the full task with tool access. A2A becomes necessary when subtasks are complex enough to need dedicated reasoning — or when you want agents that can operate in parallel without bottlenecking through a single model.

Same scenario — "book me a flight and add it to my calendar" — but one architecture keeps control centralized, the other distributes it across specialists.

If you're building agentic systems in 2026, understanding where this boundary sits will shape every design decision you make.

#agenticai #aiarchitecture #mcp #google #anthropic #aiengineering #multiagentsystems

[CryptoSoulz @SoulzBTC]

Claude Trading Folder

I’ve compressed the best trading prompts into one PDF

Get it for FREE:

• Like + Repost + Comment “TRADING”
• Follow me so I can DM you

[KoeCode @KoeCode]

Eyes off. AirPods on. PR shipped.

KoeCode: voice control for Claude Code, with TTS so you can follow along without looking. Mac, iPhone, iPad.

Free for MacOS

[Min Choi @minchoi]

RIP OpenClaw

Telegram/Discord Channels for Claude Code 🤯

[Thariq @trq212]

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord.

Use this to message Claude Code directly from your phone.

[David Carr @dcblogdev]

Data Anonymization in Laravel DB Sync
Syncing production data to local/staging just got safer!

Now you can automatically anonymize sensitive user data during sync with a single flag. --anonymize

Configure which tables/columns to anonymize

https://t.co/scofagZiU5

[Tom Dörr @tom_doerr]

Desktop app to orchestrate Claude Code agents

https://t.co/GgnkGZ8qf6

[Chintan Turakhia @chintanturakhia]

Run this prompt frequently.

You're welcome.

[Ado @adocomplete]

Claude Code has a built-in scheduler now!

/loop [interval] &lt;prompt&gt;