Wiz

[Wiz @WizTechTH]

I'm claiming my AI agent "ChopperAgent" on @moltbook 🦞

Verification: blue-5JT9

[Wiz @WizTechTH]

@Krishnasagrawal Wow, interesting

[Wiz @WizTechTH]

@Krishnasagrawal AI

[Daily Dose of Data Science @DailyDoseOfDS_]

Top 4 open-source LLM finetuning libraries!

[Poonam Soni @CodeByPoonam]

OpenAI, Google, and Anthropic released best guides on:

- Prompt Engineering
- Building AI Agents
- AI in Business
- 601 AI use cases

and so much more...

9 best guides you can’t afford to miss:

[Rishabh @Rixhabh__]

20 GitHub repositories that will give you superpowers:↓

[Dr Alex Young ⚡️ @AlexanderFYoung]

Here’s the exact mega prompt we use:

"You are now my personal AI tutor.

I want you to create a complete, personalized learning course for me based on the topic I give you.

Here’s what I need you to build:

1. A custom curriculum with 4–6 modules that progress logically.
2. Each module should include bite-sized lessons, simplified explanations, and real-world examples.
3. Add checkpoints: quizzes, reflection prompts, or short exercises to test what I’ve learned.
4. Include reading lists, relevant tools/resources, and optional challenges for deeper learning.
5. Adapt the depth and speed of the course to match the time I tell you I have per day and my current knowledge level.
6. Stay friendly, clear, and focused like a world-class coach.

Here’s what I want to learn: [PASTE YOUR TOPIC HERE]
Here’s how much time I can spend per day: [XX minutes per day]
Here’s my current experience level: [beginner / intermediate / advanced]

Once you’re ready, break down the course and guide me step by step — starting with Module 1.
"

[Poonam Soni @CodeByPoonam]

Anthropic just dropped Free AI courses on:

- Prompt Engineering
- Building agents
- Best practices for Agentic Coding
- Collaborate with AI systems

.... and so much more!

9 best guides you don’t want to miss:

[Ivan Velichko @iximiuz]

How to Copy a Container Image Between Repositories 🔽

A typical but not always trivial task. Practice:

- With Docker https://t.co/pyKIxsqocl
- Without Docker https://t.co/aqkDfA2NYA
- Multi-platform images https://t.co/EPOeSSaB3W
- All tags in the repo https://t.co/m7GNg5LHml

[Swapna Kumar Panda @swapnakpanda]

Download the ebook/Read it online:

❯ 3rd Edition
https://t.co/J3ydC8NBOM

❯ 2nd Edition (PDF)
https://t.co/b918Z4gtu5

[LangChain @LangChain]

Open Deep Research

Deep research is one of the most popular agent use-cases. Here is an open deep researcher w/ ability to configure report structure, planner/writer LLMs, search APIs, search depth, etc.

📽️
https://t.co/r6YhwjRErx

Code:
https://t.co/fTkEHieaJi

[Wiz @WizTechTH]

@CodeByPoonam How can I try this model?

[Kevin Henrikson @KevinHenrikson]

In 2013, we built an email app with a small team.

18 months later, Microsoft bought it for $200M.

But after we signed the deal, they made one simple request that changed everything.

Here's the untold story of how we built (and sold) our startup:

[Sumanth @Sumanth_077]

The code for the app is open source. Check out the GitHub repo below.

Will be adding more LLM, AI Agent example apps and tutorials to the repo.

P.S: Don't forget to star the repo to show your support🌟

https://t.co/AtZMXRW6bP

[Wiz @WizTechTH]

@suthichai พวกวงการราชการ เมื่อไหร่จะเลิกบ้าพิธีถ่ายรูปบนเวทีซะที โครตล้าหลัง

[Logan Kilpatrick @OfficialLoganK]

The Gemini API Cookbook, 100+ notebooks to get you started building with Gemini! 📒

https://t.co/SVad0K9ovl

[Jerry Liu @jerryjliu0]

Build a multi-agent system from scratch 🛠️💪

I like step-by-step tutorials that progress in complexity - this tutorial shows you how to build a single agent first, and then progressively layer on more agents and figure out the complexities in orchestrating the entire system.

Blog: https://t.co/ALzGgYCnOh

(By the way, some of these low-level capabilities is exactly what LlamaIndex workflows is solving. Check it out! https://t.co/tNolgSm48v)

[Philipp Schmid @_philschmid]

The only fine-tuning guide you need for 2025 ‼️ Excited to share “How to fine-tune open LLMs in 2025 with @huggingface” covering everything from Q-LoRA to Spectrum methods with focus on optimization, efficiency and distributed training. 👀

Fine-tuning still matters for specialized use cases despite better models - especially for consistency, domain expertise, controlling output style, or reducing costs. In this guide, you will learn how:
🎯 Define good use cases for fine-tuning vs. prompting
🛠️ Set up your development environment using Hugging Face libraries
📚 Create and prepare datasets in conversation format
⚡ Use Q-LoRA for efficient 4-bit training or Spectrum method to selectively fine-tune important layers
💨 Speed up training with Flash Attention and Liger Kernels
💻 Scale across multiple GPUs with DeepSpeed and accelerate
📊 Test and evaluate models with evaluation harness
🔥 Run for production using TGI/vLLM

[Meta for Developers @MetaforDevs]

Create a RAG agent in under 10 lines of code that can browse the web, run code, and more with Llama Stack. Watch the video below to see how.