All articles

10 in-depth guides, from how a transformer predicts the next token to running agents in production. Filter by topic or level, or press / to search.

Showing 10 articles

Fundamentals01

What Is a Large Language Model?

Tokens, the transformer, attention and the training pipeline from pretraining to RLHF, explained without hand-waving.

Beginner8 min read

Fundamentals02

Chain of thought, test-time compute, RL with verifiable rewards and thinking budgets: when a slower answer is a better one.

Intermediate9 min read

Model types03

Spectrograms, Whisper, word error rate, diarization, vocoders, codec-based TTS and the latency budget of a voice agent.

Beginner10 min read

Model types04

Classic OCR pipelines, Tesseract, layout analysis, Donut and VLMs, schema-based extraction and how to measure accuracy.

Beginner9 min read

Model types05

Jev, d1-ultra and the new class of models that return calibrated yes/no, choice and score answers instead of text.

Intermediate8 min read

Building with AI06

Embeddings, chunking, vector search, hybrid retrieval and reranking: how RAG grounds answers in your own documents.

Intermediate10 min read

Building with AI07

Tool calling, the agent loop, workflows versus agents, the Model Context Protocol, tool design and agent security.

Intermediate9 min read

Building with AI08

The loop, tools, context handling and permissions around a model decide how well an agent works. How harnesses are built and judged.

Advanced10 min read

Building with AI09

Patterns, architecture, structured outputs, human approval and reliability for LLM-powered workflows, with a support-triage example.

Intermediate9 min read

Building with AI10

Memory maths, quantization, llama.cpp, Ollama, vLLM and LoRA: how to run and adapt open-weight models on your own hardware.

Advanced10 min read