bergen, norwayvol. i · no. 20 · July 17, 2026rss feed

Hasan Arief

A lab notebook on agentic coding, open-weight models, and what they cost to run

The Guides

Long-form, evergreen, updated in place

Each guide is revised as the field moves and carries a changelog. Shorter day-to-day findings live in notes.

Karpathy's LLM wiki: a knowledge base your coding agent maintains

Karpathy's LLM wiki: point a coding agent at a markdown folder and let it maintain the knowledge base. What it is, why it earns its place, and how to set it up.

· 9 min read

Claude Code in 2026: the agentic loop, capabilities, and architecture

A maintained third-party reference to Claude Code: the agentic loop, built-in tools, context window behavior, environments, safety model, and extension layer.

· 4 min read

Open-weight LLMs for coding in 2026: hardware and real costs

Open-weight coding LLMs as of July 2026, GLM-5.2, Kimi K2.7, DeepSeek-V4, with the VRAM math, GPU rental prices, and when self-hosting beats an API.

· 6 min read

OpenAI Codex in 2026: capabilities, surfaces, and how it works

A maintained third-party reference to OpenAI Codex: the CLI, IDE, cloud and app surfaces, AGENTS.md configuration, skills, MCP support, plans and access.

· 5 min read

Setting up Claude Code in 2026: install, CLAUDE.md, skills, hooks, memory

Practical Claude Code setup for 2026: install on Mac, Linux or Windows, authenticate, run /init, add skills and hooks, and stay safe with git.

· 6 min read

Agent orchestration patterns in 2026: subagents, teams, and pipelines

A map of agent orchestration in 2026: five coordination levels from a single session to agent teams, with failure modes and selection criteria.

· 8 min read

Codex CLI vs Claude Code: what I learned running both daily

An honest Codex CLI vs Claude Code comparison from running both daily on one codebase: strengths, config interop, and the two-model workflow that emerged.

· 6 min read

AGENTS.md and CLAUDE.md best practices: one instruction file for every coding agent

How to write AGENTS.md and CLAUDE.md files: what to include, the 200-line size target, monorepo precedence, imports, and one-source-of-truth setup.

· 7 min read

Agentic coding best practices: what works in 2026

Field-tested agentic coding best practices from daily Claude Code and Codex work: verification loops, context discipline, hooks, and review gates.

· 9 min read