Model Context Protocol (MCP) standardizes tool communication, enabling AI coding agents to perform complex tasks like executing commands, interacting with web browsers, and integrating local or cloud resources. MCP servers broaden AI applications beyond coding. In machine learning, use AI tools to help optimizing data engineering, model deployment, and augmenting typical machine learning tasks.
Best models for vibe-coding: Gemini 2.5 Pro, Claude 3.7 Sonnet, DeepSeek R1 + Claude 3.5. Agent modes: Architect vs Code, and Boomerang Mode. Explores using local models for enhanced privacy, fine-tuning models on specific codebases, and practical tips for power-usage of Roo Code, such as judicious @ usage and managing concurrent feature developments efficiently.
Compares popular AI coding plugins and IDEs: Cursor, Cline, Roo Code, Aider, Github Copilot, Windsurf. AI is transforming coding through a "vibe coding": leveraging LLMs with tool-calling to assist in code generation and testing. Many AI-driven IDEs and plugins are evolving rapidly, offering diverse agentic capabilities, each with unique strengths.
Transformers architecture, of Large Language Model (LLM) and 'Attention is All You Need' fame
Databricks emerges as a compelling platform in the realm of data analytics and machine learning operations. Combined with its versatile Delta Lake and integrations with major cloud providers, it offers a robust solution for both beginners and enterprises, covering data analytics and machine learning needs.
Conversation with Dirk-Jan Kubeflow (vs cloud native solutions like SageMaker)
Chatting with co-workers about the role of DevOps in a machine learning engineer's life
Part 2 of deploying your ML models to the cloud with SageMaker (MLOps)