Anthropic shipped Claude Sonnet 5 on June 30 at $2/$10 per million tokens, closing most of the capability gap to Opus 4.8 at a third of the price — while Fable 5 spent 19 days pulled from the market under US export controls before returning July 1 with a stricter cybersecurity classifier. What actually changed, what the benchmark table hides, and which tier real workloads should run on now.
Claude-Code
-
Claude Sonnet 5 and Fable 5: The New Generation, Priced and Positioned -
AI-Assisted Coding: The Complete Developer's Guide to Tools, Agents, and Local Models A deep dive into the AI coding ecosystem — Claude Code, Google Antigravity, MCP servers, Cursor, Windsurf, Continue.dev, Aider, and running powerful models locally with Ollama and LM Studio.
-
Version Control Mastery: Git, GitHub, AI Agents, and the Home Lab Stack A comprehensive deep-dive into version control systems — from Git's internal model to advanced CLI tricks, branching workflows, GitHub power features, AI-assisted workflows, and running a self-hosted Git platform in your home lab with Gitea, Forgejo, and Woodpecker CI.
-
Claude Fable 5 vs Opus: A Realistic Look at Whether You Need the Mythos-Class Model Anthropic just released Claude Fable 5, the first public Mythos-class model, at double the price of Opus 4.8. A realistic breakdown of where the capability gap actually shows up, where it does not, the safety-routing wrinkle, and a decision framework for when to pay for Fable versus staying on Opus or Sonnet.
-
What AI Coding Tools Actually Cost: Subscriptions vs Usage vs Raw API in 2026 A practical cost comparison of the major AI coding tools in 2026 — Claude Code, Cursor, GitHub Copilot, Windsurf, OpenAI Codex, Gemini CLI, and the open-source BYO-key tools Aider and Cline — covering what each costs, what you can actually accomplish at each price tier, and the central question: when does a flat subscription beat paying raw per-token API pricing, and when does bringing your own API key win? With the real break-even math, vendor API rates, and the 2026 shift to usage-based billing.
-
AI in the Terminal A practical guide to AI-assisted development and automation in the terminal — Claude Code for agentic coding, aider for pair programming, the llm CLI for pipelines, fabric for pattern-based text processing, and how to integrate LLM output into shell workflows without creating new problems.
-
OpenClaw: The Complete Guide to Self-Hosted AI Agents Everything you need to know about OpenClaw — the open-source, self-hosted AI agent that connects your messaging apps to real-world actions. Covers its origins and confusing rename history, the architecture, deployment on Docker, Mac mini, and a VPS, running it against local models with Ollama, the SOUL.md policy system, the serious security incidents you must understand before deploying, and an honest comparison against Claude Code.
-
The Vibecoder's Home Lab: Running AI Agents Across Multiple Machines A comprehensive technical guide to building a home lab purpose-built for AI-assisted development — covering hardware selection, network architecture, DNS, Proxmox virtualization, shell configuration, running parallel Claude Code agents with git worktrees and tmux, agent sandboxing, and the workflows that make vibecoding genuinely efficient.