Gemini 4 Carbon: what it is and why you can't use it yet
Gemini 4 Carbon is Google's strongest security model, but only selected teams can use it. What it does, why it launched closed, and what to use today.
· 6 min
Tools
13 articles
GitHub Octoverse 2026: 40% of pull requests now start with an agent
GitHub's Octoverse 2026 shows 40% of pull requests now start with an AI agent. The key numbers, and what the teams where it works do differently.
· 6 min
Claude ported the TypeScript compiler to Rust without anyone reading the code: why it worked
A developer let Claude Opus 5.5 translate the TypeScript compiler to Rust for two weeks. It passes all 184,749 tests and he says he never read a line. What happened, what's overhyped, and how to use the same structure for a migration in your own project.
· 7 min
Jev: the AI model that decides instead of writing
TypeSafe launched Jev, an AI model that doesn't generate text: it answers closed questions about a piece of text in a tenth of a second, for a fraction of the price. What it is, how to use it, where it fails, and how to try it.
· 10 min
Opus 5.5: what changes if you code with an AI agent
Anthropic released Claude Opus 5.5: cheaper, faster, and with three new restrictions. What it does to the bill for a real session, when fast mode is worth it, who it breaks things for, and how to test it on your repo.
· 8 min
Choosing a coding agent is no longer choosing a model
Claude Code, Codex, Copilot and Cursor now run the same frontier models and cost roughly the same. What separates them is the harness: how much you supervise, how much you delegate, and where it runs. How to choose by the work.
· 7 min
Claude Code best practices, to move fast without losing quality
Coding fast with an agent and coding well aren't the same thing, but they're not contradictory either. The habits and tools — CLAUDE.md, plan mode, subagents, hooks — that keep code scalable and clean, even when Claude wrote it.
· 11 min
Claude Skills, from the basics to building your own
A Skill is a folder with instructions that Claude reads on its own when it's needed, without taking up context until then. How to use the ones that already exist, how to build your own step by step, and what to check before installing someone else's.
· 8 min
Archify: the skill for verified architecture diagrams in Claude Code or Codex
Archify is a free skill for Claude Code, Codex, Cursor, and opencode that draws verified architecture diagrams instead of invented ones: it splits writing a typed description of the system, validating it, and only then drawing it.
· 11 min
Headroom compresses what your AI agent reads, before it reaches the model
A coding agent can burn half its tokens on a log or a JSON blob that never needed to be sent whole. Headroom is a free tool that compresses that before it reaches the model, without changing the answer, and without sending your code anywhere to do it.
· 8 min
You use four Claude Code commands. Ten are missing
Ten commands that solve the same four problems you already have: the context that fills up, the setup you never did, the change that has to be undone, and the work that does not fit in one turn.
· 8 min
Three tools you need to know exist for coding with Claude
Three free tools you need to know exist. One imposes a way of working before any code gets written. Another shows you where your tokens go. The third gives it design judgement. What each one does, how to install them, and what they cost you.
· 7 min
Five Git commands that get you out of trouble
You deleted a commit, something broke and you do not know when, or you need to undo something you already pushed. Five commands almost nobody uses until they need them, explained with the exact situation that calls for each one.
· 5 min