AI, decoded for the net

A clear, no-nonsense introduction to modern AI: who builds it, how the core ideas work, and how to use the tools with better judgement.

Major AI players

ChatGPT, the GPT-5.6 model family, multimodal models, and the Responses API.

Claude Fable 5, Opus 4.8, Sonnet 5, Haiku 4.5, and tools for long-running agents.

Gemini 3 models, native multimodality, generative media, and Google's developer platforms.

How language models work
A practical mental model of tokens, training, context, and why fluent answers can still be wrong.
What AI agents are
How models, tools, memory, and control loops combine into systems that can carry out multi-step work.
Multimodal AI explained
How one system can work across text, images, audio, and video—and where modality-specific checks still matter.
How Codex CLI works
A mental model of the interactive agent, repository context, configuration layers, tools, and verification loop.
Codex CLI workflows and commands
When to use interactive sessions, exec, resume, review, profiles, slash commands, and machine-readable output.

Write better prompts
A repeatable way to give AI systems clear goals, useful context, and checkable requirements.
Verify AI-generated work
A risk-based checklist for checking facts, calculations, code, and recommendations before relying on them.
Use AI with sensitive data
A practical method for deciding what data to share, reducing exposure, and choosing safer workflows.
Codex CLI best practices
A practical workflow for scoping tasks, supplying context, steering the agent, testing changes, and reviewing the diff.
Best practices for Claude Code
A practical, evergreen walkthrough for getting reliable results from Claude Code.
Write an effective AGENTS.md
How to give Codex durable repository guidance without filling its context with vague or stale rules.
Codex CLI permissions and sandboxing
Understand sandbox modes, approval policies, network access, protected paths, and safer automation defaults.