Field notes for agent builders.

HarnessTax: How Much Does the Harness Matter for Coding Agents?

What does a coding-agent harness actually add, and at what cost? UC Berkeley Sky Lab evaluated 21 model–harness pairs — seven models across Claude Code, Codex CLI, and Pi on SWE-bench Lite and Terminal-Bench 2.0. The harness barely moves success rate (±2–5%) but can swing cost up to 5×. A minimal four-tool open-source harness matches frontier success at a fraction of the cost, and models frequently win outside their own provider's harness — your Claude models may not need Claude Code.

Building claude-session-management

A Global Workspace in Language Models

Anthropic discovers that Claude developed an internal J-space — a privileged mental workspace analogous to the global workspace theory of conscious access in neuroscience. It emerged on its own during training, enables silent reasoning, and can be used to detect hidden goals and deception.

The New SDLC With Vibe Coding

A comprehensive whitepaper by Addy Osmani, Shubham Saboo, and Sokratis Kartakis exploring how AI transforms the software development life cycle — from casual vibe coding to disciplined agentic engineering, context engineering, the factory model, and the economics of AI-driven development.

How Your Agents Can Write and Optimize Their Own Skills

A deep dive into automated skill optimization frameworks — SkillOpt, GEPA, and EvoSkill — that treat agent skill files like trainable neural network parameters, enabling agents to iteratively debug, validate, and update their own skills without touching model weights.

Copilot Cowork Is Now Generally Available — Anthropic Claude Meets Microsoft 365

Microsoft's Copilot Cowork — the deep-work AI assistant powered by Anthropic Claude — is now GA for all Microsoft 365 Copilot users. Brings model choice (Opus 4.8, Sonnet 4.6, GPT 5.5), partner plugins (Monday.com, Miro, Adobe, Atlassian), and Edge browser access.

LangChain Deep Agents — The Batteries-Included Agent Harness, Explained

LangChain open-sourced Deep Agents — an opinionated, batteries-included agent harness built on LangGraph. Inspired by Claude Code, it ships with planning, filesystem access, sub-agent orchestration, context management, and persistent memory out of the box.

How to Build a Software Factory with Claude Code: From Vibe Coding to Agentic Development

Comprehensive freeCodeCamp handbook by Qudrat Ullah on building a structured AI-assisted development workflow. Covers the five layers of AI-assisted development (context, knowledge, agents, workflows, delivery), seven specialized subagents (codebase-researcher, story-writer, spec-writer, backend-builder, frontend-builder, test-verifier, implementation-validator), orchestrator design, CLAUDE.md best practices, skills, hooks, and a complete PR review checklist. Includes hands-on setup for Next.js/Node.js projects.

Using Claude Code: The Unreasonable Effectiveness of HTML

Anthropic's guide to using HTML instead of Markdown as Claude Code output format — information density, visual clarity, two-way interactions, and custom editing interfaces.

Apple TV's New Cyberpunk Series Is the Sci-Fi Gamble That Could Change Everything

Το Neuromancer του Apple TV+ βασίζεται στο εμβληματικό cyberpunk μυθιστόρημα του William Gibson. Με dual-world setting (Sprawl + matrix cyberspace), fast-paced noir storytelling και cast με Callum Turner και Briana Middleton, η σειρά φιλοδοξεί να γίνει η κορυφαία sci-fi παραγωγή της πλατφόρμας.

The 4 Lines Every CLAUDE.md Needs

Why a GitHub repo with just four behavioral guidelines for CLAUDE.md got 60,000 stars. Inspired by Andrej Karpathy, the article argues that behavioral constraints — not feature checklists — are the real bottleneck in AI-assisted coding.