Rami Krispin's Data Science Channel

Getting Started with Docker Sandboxes 🚀 This tutorial from Docker walks through setting up an isolated development environment for AI-assisted coding. The five-minute tutorial covers: ✅ Installing the Sandbox CLI ✅ Authenticating with Docker ✅ Launching a sandbox ✅ Mounting a workspace ✅ Using the same sandbox with Claude and Codex 📽️: https://www.youtube.com/watch?v=9jfk1fdhXZo

ML System Design for Data Scientists 🚀 This video from Andres Vourakis, a Senior Data Scientist at Nextory, walks through a production ML system design framework. The 17-minute video covers: ✅ Six-step design framework ✅ Four production requirements ✅ Trial-to-paid conversion example ✅ Layer-by-layer system design ✅ Interactive ML system map 📽️: https://www.youtube.com/watch?v=t3W3TJrNUnQ

The first tutorial in this series is out and focuses on the motivation for using Docker. https://theaiops.substack.com/p/why-ai-developers-should-learn-docker

Docker 101 🐳👇🏼 Want to learn Docker? I am starting a new series of tutorials focused on Docker for ML/AI developers. The first tutorial is out. Docker isn't as hard as it sounds, but it has a steep learning curve, and the goal of this series is to smooth it out. What are the benefits of Docker? Reproducibility. Reproducibility is critical in any form of software development, mainly when you ship your code to another machine (e.g., deploy or have teammates run it). This Docker series is going to cover: ✅ What is Docker and when should you use it ✅ Containerizing a minimal Python AI application. ✅ Writing Dockerfiles that remain fast and maintainable as a project changes. ✅ Building reproducible environments with Docker Compose and Dev Containers. ✅ Running local models with Docker Model Runner. ✅ Designing container boundaries for agents, MCP tools, and Docker Sandboxes. ✅ Testing, securing, and publishing multi-platform images through CI.

Meta Muse Glimmer 🚀 Meta released a 30B open-weight agentic model under Apache 2.0 for local workflows on consumer hardware. It supports tool use, long-horizon reasoning, failure recovery, text+image input, adjustable reasoning effort, and 100+ languages. A roughly 4-bit version fits under 20 GB. More details: https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model

Hermes Desktop Workflows 🚀 This video from Tonbi's AI Garage walks through recent Hermes desktop workflows. The 16-minute video covers: ✅ Remote machines over SSH ✅ Multi-session panes and tabs ✅ Drag-in session context ✅ Custom widgets with the Plugin SDK ✅ The Kanban plugin ✅ Agent delegation across researcher, writer, and verifier profiles 📽️: https://www.youtube.com/watch?v=bifDX18uyUk

I feature a data science book every week in my newsletter, and last week's pick focuses on Transformers: The Definitive Guide - Applications Beyond NLP by Nicole Königstein. The book starts with attention, embeddings, and transformer architecture, then shows how the same ideas extend across different data types and applications. Topics include: ✅ Time-series forecasting and anomaly detection ✅ Computer vision and image segmentation ✅ Image, video, audio, and music generation ✅ Reinforcement learning and world models ✅ Reasoning, coding, and AI agents ✅ Model optimization and production deployment It is aimed at intermediate-to-advanced machine learning engineers, data scientists, and researchers who want to understand where transformers fit beyond language tasks. More details are available here: https://learning.oreilly.com/library/view/transformers-the-definitive/9781098167004/ 📌 Subscribe to my newsletter: https://ramikrispin.substack.com/

Claude Code Full Course 🚀 This course from freeCodeCamp, developed by EricWTech, walks through Claude Code setup and day-to-day workflows. The 82-minute course covers: ✅ VS Code setup ✅ Permission modes ✅ Plan mode and autonomous goals ✅ Claude skills ✅ Context and token usage ✅ Slash commands ✅ GitHub version control ✅ MCP tools and app deployment 📽️: https://www.youtube.com/watch?v=7l6bXLAKyEI

I am starting a new series of tutorials focusing on Docker 🐳 for ML/AI Ops 👇🏼 I recently released a new LinkedIn Learning course focused on Docker for AI/ML developers. While creating this course, I spent a lot of time preparing learning materials, and I decided to turn those materials into a sequence of tutorials. Here is what this Docker series is going to cover: 🔹What is Docker and when should you use it 🔹 Containerizing a minimal Python AI application. 🔹 Writing Dockerfiles that remain fast and maintainable as a project changes. 🔹 Building reproducible environments with Docker Compose and Dev Containers. 🔹 Running local models with Docker Model Runner. 🔹 Designing container boundaries for agents, MCP tools, and Docker Sandboxes. 🔹 Testing, securing, and publishing multi-platform images through CI. The tutorials will be available in my AIOps newsletter 🗞️ Please subscribe to receive the tutorials 👉🏼 https://theaiops.substack.com/

Issue 100 is out! 🔹 Open Source of the Week - Prime Agent 🔹 New learning resources 🔹 Book of the week - Generative AI at AWS https://ramikrispin.substack.com/p/prime-agent-generative-ai-at-aws

Stanford CS229 Machine Learning - Spring 2026 🚀 Stanford Online released a 17-lecture playlist from its graduate machine learning course. It provides a structured path from supervised learning foundations to modern generative models and reinforcement learning. The course covers: ✅ Supervised learning setup ✅ Weighted least squares ✅ Generalized linear models ✅ Gaussian discriminant analysis ✅ Dataset splits and ML advice ✅ Neural network architecture and backpropagation ✅ K-means, Gaussian mixtures, and PCA ✅ Diffusion and representation learning ✅ LLMs, transformers, and in-context learning ✅ Reinforcement learning and policy gradients Playlist 📽️: https://www.youtube.com/playlist?list=PLaqpC4kq8Gpw

Terraform Crash Course - Infrastructure as Code 🚀 This tutorial from NeuralNine provides a practical introduction to Terraform. It moves from installation and a minimal AWS example to combining AWS services, then shows smaller examples with GCP and Docker. 📽️: https://www.youtube.com/watch?v=pnzlqoYNuQc

Why AI Agents Need a Context Layer 🚀 This talk from MotherDuck's Bev Turnbaugh explains why correct SQL is not enough when an agent lacks a company's business definitions. It covers semantic vs. context layers, RAG and rules files, MotherDuck guides, and an MCP walkthrough that surfaces relevant context alongside the data. 📽️: https://www.youtube.com/watch?v=hmjRc6KJ-hw

Issue 99 is out! This week's agenda: 🔹 Open Source of the Week - Forge3D by Milos Popovic, PhD 🔹 New learning resources - Codex workflows, local model fine-tuning, context layers for AI agents, and Terraform 🔹 Book of the week - Transformers: The Definitive Guide by Nicole Königstein https://ramikrispin.substack.com/p/the-forge3d-project-transformers

Fine-Tune AI Models Locally with Unsloth Studio 🚀 This tutorial from Tech With Tim walks through fine-tuning an open model locally with Unsloth Studio. It covers fine-tuning basics, LoRA vs. QLoRA, model and dataset setup, training, comparing the result with the base model, and exporting the model. 📽️: https://www.youtube.com/watch?v=4JofSJIrjwU

Setting Yourself Up for Success with Codex 🚀 This workshop from Jason Liu, an AI Engineer from OpenAI, walks through a practical Codex workflow. This 75-minute workshop covers personal memory vaults, long-running project threads, collaboration between threads, skills and plugins, computer use, scheduled automations, goals with verification, and choosing lower reasoning levels when the task does not require extra thinking. 📽️: https://www.youtube.com/watch?v=il1c1a2FufU

Issue 98 is out! This week’s agenda: 🔹 Open Source of the Week - AI-Lake by Thiago Egon Lange 🔹 New learning resources - Hermes Agent fundamentals, Pi Coding Agent, GraphRAG in Python, Codex for beginners, Graphify with Obsidian, visual Python course 🔹 Book of the week - Designing Data-Intensive Applications, 2nd Edition by Martin Kleppmann and Chris Riccomini https://ramikrispin.substack.com/p/the-ai-lake-project-codex-for-beginners

This is a great summary about how to orchestrate AI applications with Graph and tools such as Claude Code 👇🏼 📽️: https://www.youtube.com/watch?v=QRh1a5qvm9U

Polars Crash Course - Modern Data Frames in Python 🚀 The following tutorial by NeuralNine provides a one-hour introduction to Polars, moving from installation and core DataFrame operations to expressions, joins, lazy query planning, streaming, GPU parallelism, and plotting. It is useful for Python users who want a structured comparison with Pandas. 📽️: https://www.youtube.com/watch?v=OlsRyy-au0E

Hermes Agent Fundamentals in 29 Minutes 🚀 The following tutorial by Tina Huang provides a 29-minute introduction to Hermes Agent. It includes a companion resource package and links to related material on local agents and open source AI, making it a useful starting point for exploring the broader ecosystem. 📽️: https://www.youtube.com/watch?v=5_N84t1rUU0