AI ENGINEERING
AI Terminology: Agents, Skills, RAG, MCP, and the Layers Beneath the Hype
A practical mental model for AI terminology: prompt, context, memory, agents, RAG, function calling, MCP, workflows, skills, and sub-agents.
The notebook / 64 articles
Ideas into practice
Notes on LLMs, machine learning, data engineering, and the systems that make them work.
Showing 21–30 of 64 posts
LARGE LANGUAGE MODELS
ChatGPT in 2025: A Year in Review
A visual recap of my year with ChatGPT in 2025, collecting usage statistics and personalized summary cards.
AI ENGINEERING
The Mandate for Leadership in AI Engineering
Over the next 12 to 24 months, the differentiator among engineers will shift from mastery of programming languages like Rust, Go, or Python, or the volume of code produced, to the...
LARGE LANGUAGE MODELS
LLM Interview Questions
Language models learn distributions over tokens; useful applications also depend on sound evaluation, efficient training and inference, and reliable access to evidence. These...
LARGE LANGUAGE MODELS
LLM Training Epoch
As large language models (LLMs) scale up, researchers have begun to notice a growing imbalance between model size and the availability of high-quality training tokens. The...
LARGE LANGUAGE MODELS
vllm throughput
vLLM pre-allocates a block of GPU memory for KV-cache based on the --gpu_memory_utilization parameter. By increasing this parameter, you free up more contiguous space for KV...
AI ENGINEERING
LangGraph Reflection
Reflection is related to agent self-improvement or reasoning feedback loops.
AI ENGINEERING
LangGraph Sample Project
A LangGraph sample project with separate research, analysis, and supervisor services, REST communication, and retry handling.
AI ENGINEERING
LangChain/LangGraph Q&A
LangGraph’s core philosophy is to orchestrate multi-step, stateful agent workflows using a directed graph (DAG or DG) structure. Each step is modeled as a node, while data and...
LARGE LANGUAGE MODELS
Training LLM From Zero
The goal of this project is to design, implement, and train a small-scale Large Language Model (LLM) from scratch, progressing through the full training lifecycle: