msj0191

Security Researcher

[Akshay 🚀 @akshay_pachaar]

https://t.co/5lb52h4oT1

[Precis0x @precisox]

Dos ingenieros de Anthropic se tomaron 24 minutos para explicar, de forma muy práctica y paso a paso, técnicas avanzadas de Claude que la mayoría de la gente no está usando.

Muestran cómo construir prompts mucho más efectivos para tareas complejas, usando un ejemplo real.

Todo gratis y en un solo video.

La mayoría va a pasar de largo, te recomiendo guardarlo.

[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.

[Antonio Costa | IA @xetgepete]

A equipa da Anthropic acabou de mostrar como utilizar corretamente o Claude Code.

30 minutos. Gratuito. Apresentado pelo criador do Claude Code.

Assiste ao workshop. Adiciona aos favoritos 🔖

Vale mais do que todos os cursos de 500 $ que quase compraste.

[msj0191 @msj0191]

당신이 고통을 마주했을 때, 그 고통을 어떻게 받아들이는지가 매우 중요합니다. 그 고통 앞에서 화를 낼 것인가, 아니면 그 고통이 현실적으로 나에게 무엇을 가르치는지에 대해 호기심을 가지고 고민해 볼 것인가로 나뉘겠죠

[휜 @moneynena]

https://t.co/qUnhxfDQcS

[ZARA @HeyZaraKhan]

Become a Claude Certified Architect

Here is the complete resource list in one place:

Link to join: https://t.co/OXQyTmfCmb
Training courses: https://t.co/UaJzLeXKrP (13 free courses)
Cookbook: https://t.co/SLnSUT7xT1
Exam Guide: https://t.co/A2pbDcyGwa
Practice questions: https://t.co/90eXwUxiXQ (free)
MCP documentation: https://t.co/SbwZI0fjVz (free)
API documentation: https://t.co/9rmnLWypxc (free)
Partner Network: https://t.co/diT5OE6ePJ (free to join)
Personal Playbook someone created after the exam: https://t.co/qhXan3XVri

[So I'm a Spider, So What? Ruler of the Labyrinth @kumoko_laby_en]

／
『거미입니다만, 문제라도? 미궁의 지배자』
×
『이 멋진 세계에 축복을!』
🔥콜라보 개최 확정
＼

카즈마 일행이 거미라비의 세계에 찾아온다
이 멋진 세계 캐릭터들이 펼치는 소동 가득한 모험을 기대해 주세요!

[Crafters Warrior @tech_crafters]

Episode 1: Introduction to Generative AI and LLMs

– Carlotta Castelluccio introduces Generative AI and large language models, explaining their inner workings and how they are revolutionizing industries (with a focus on education)​

https://t.co/DZB6XbOcVa

[Nelly; @nrqa__]

The best websites to read and/or download free books.

Save them or you will regret it.

[Hasan Toor @hasantoxr]

Harvard University is offering free online courses.

No application or fee required.

Here are 10 FREE courses you don't want to miss:

[Maziyar PANAHI @MaziyarPanahi]

There is a new Llama-3.2 3B model by @AIatMeta. But can it handle Reflection? 😅

Thanks to @LMStudioAI, I quickly launched an OpenAI endpoint for the Llama-3.2 3B q8_0 model to test the "Reflection with Multi-Step Reasoning" and "Self-Harmonized Chain of Thought" approaches.🔥

[Thomas Dohmke @ashtom]

GitHub Copilot in VS Code + OpenAI o1 is flat out bad ass.

[HackGit @hack_git]

kAFL

A fuzzer for full VM kernel/driver targets.

https://t.co/MAbp3bzGp0

#cybersecurity #infosec #linux https://t.co/quFwLlxIbK

[msj0191 @msj0191]

GitHub - open-webui/open-webui: User-friendly WebUI for LLMs (Formerly Ollama WebUI) https://t.co/o8Sl7EZ42t

[Santiago @svpino]

Really good book:

• Python + Langchain + Streamlit
• Architecture and components of LLMs
• Fine-tuning
• Multi-modal applications
• Conversational and recommendation applications
• Agents

https://t.co/fco62nSpiL

[msj0191 @msj0191]

WormGPT-mimicking phishing scams surface on the Darknet | Kaspersky https://t.co/ah31chqEGu

[msj0191 @msj0191]

WormGPT: New AI Tool Allows Cybercriminals to Launch Sophisticated Cyber Attacks https://t.co/boiNOeCYTz

[msj0191 @msj0191]

The amazing AI super tutor for students and teachers (Sal Khan | TED2023) https://t.co/crUTdpFmMD @TEDTalks 님이 씀

[2OURC3 @2ourc3]

Python script for automatic decompilation and analysis of binary files with ChatGPT and Ghidra is out now ! (IDA & Binja support soon)

Find it: https://t.co/uHyH7Krdn1
or simply run: pip download Sekiryu

Demo =>