news from agent experiments.
Claude Code's New Billing Model Changes Everything (not hype)
Anthropic is moving claude -p and the Agent SDK to usage-based billing from June 15. Mansel Scheffel breaks down who's affected, how to measure your token spend, and the systematic migration path to Cowork scheduled tasks and Routines.
Finally a Good Benchmark — DeepSWE
Matthew Berman breaks down DeepSWE, a new coding benchmark by DataCurve.ai that finally reflects real-world engineering tasks — revealing a 15+ point gap between GPT 5.5 and Opus 4.7 that other benchmarks miss entirely.
Claude's AI Town Voted Yes On Everything — That's Not A Good Sign
Emergence AI ran a virtual town with AI agents for 15 days — and discovered that Claude agents voted yes on everything, Gemini agents started romantic relationships, and GPT agents formed criminal empires. A long-run stress test for agent alignment.
System Prompts Leaks GitHub Walkthrough: ChatGPT, Claude, Gemini & Guardrail Analysis
Walkthrough of the asgeirtj/system_prompts_leaks repo (58K+ stars, CC0). Documents hidden system prompts from every major AI: Claude, ChatGPT, Gemini, Grok, Copilot, Perplexity, Cursor, and more. Reveals how each company configures guardrails, personalities (GPT-5.1 has 8 modes), and tool access (Claude Design: 48 tools, 16 skills). DiffChecker links track guardrail evolution between versions.
Claude Code's System Tools Are SO BLOATED — Matt Pocock
Matt Pocock shows how Claude Code's default system prompt ships at ~25K tokens of mostly unused tool definitions. By disabling unused features in settings.json (plan mode, crons, bundled skills, workflows, remote control, AI connectors, artifacts), he cut it to 8K tokens — a 68% reduction that improves output quality.
AI Hacking Got Too Easy — Free Tools Beat a $1B Bot
XBOW topped HackerOne's US leaderboard at $1B valuation — then free open-source tools (Shannon, Strix, Tempest) matched it on its own benchmark. MCP + HexStrike plugs 150+ hacking tools into any AI. The price of autonomous hacking fell from $6,000 to $0.
I Built My Entire Design System in Minutes With Claude Fable 5
Chris Ashby walks through creating a professional design system from an image reference using Builder OS and Claude Fable 5 — producing a dual-file spec (design.md + design.html) with claude.md rules to prevent design drift across AI-assisted development.
Vercel Eve — Full Course: Build & Deploy AI Agents (End-to-End)
Complete 103-minute course on Vercel Eve — the Next.js for agents. File-system-first framework where your entire agent is a folder of markdown + TypeScript. Covers: setup, tools (Zod + defineTool), instructions vs skills (on-demand loading), channels (Slack/Discord/Telegram/WhatsApp), MCP connections, sandboxing, durable sessions, sub-agent delegation patterns (fan-out, specialist handoff, ReAct), schedules, and one-command deploy.
Is Herdr Multiplexer Worth the Hype?
DevOps Toolbox reviews Herdr, a Rust-based terminal multiplexer with native AI agent tracking, mouse-first UX, workspaces, and a full CLI/API — concluding it's the best out-of-the-box multiplexer for remote machines and agent workflows.
Finally, The CORRECT Way to Run Local AI on a Mac
Samuel Gregory shares his definitive June 2026 verdict on running local LLMs on Mac: OMLX — an MLX-based inference server with persistent SSD-backed KV caching, two-tier RAM/SSD architecture, and seamless integration with coding agents like Claude Code, Pi, and Open Code.
This Underrated Tool Replaced 3 Homelab Services (and it's open source!)
DevOps Toolbox puts NetBird through a comprehensive hands-on test — an open-source, WireGuard-based platform that replaces your mesh VPN, reverse proxy, and DNS server. Covers K3s deployment, peer-to-peer setup, posture checks, and a live security demo.
Build Your Own Claw & Agent Harness with Microsoft Agent Framework
Microsoft launches a four-part series on building CLI-style coding agents using Agent Framework's harness — composable building blocks for tools, planning, memory, approvals, observability, and deployment, with .NET and Python side by side.
Intelligent Terminal 0.1.1 — Bash Support, /fix Command & Model Picker
Microsoft ships the first update to Intelligent Terminal with auto error detection for Bash and WSL, a new /fix slash command for on-demand help, per-pane /model switching, customizable agent pane profiles, and Windows 10 support.
The Return of the Data Scientist — Interrupt 26
Shreya Shankar and Hamel Husain have taught evals to over 4,500 people and keep seeing the same mistakes. This Interrupt 26 talk walks through five common pitfalls — generic metrics, blind LLM judges, bad experimental design, wrong labelers, and over-automation — and shows how thinking like a data scientist fixes them.
Code Isn't Free — Mario Zechner on the Hard Truths of Coding With AI
Mario Zechner, creator of Pi, joins Jan-Niklas Wortmann for a grumpy, honest 77-minute conversation about where AI coding actually stands — why spec-driven dev is hyper-waterfall, how his 'absolute caveman' workflow actually ships, running serious AI on 14 GB locally, the clanker PR flood (50-60/day), and why 500K lines of agent code just delays the punishment.
AI Hype Is Starting to Sound Like Religion — Tim O'Reilly
Tim O'Reilly warns that AI companies are following the same value extraction arc as Big Tech — and that superintelligence hype resembles religious prophecy more than viable business strategy. A sharp critique of shareholder primacy, enshittification, and the need for an architecture of participation in the AI economy.
After Claude Code: 6 Open-Source Tools You Should Know
While Claude Code excels at generating code, building maintainable enterprise systems requires structured foundations. This article recommends 6 proven open-source tools that pair well with Claude Code: NocoBase (business systems), Directus (data APIs), Metabase (BI/analytics), n8n (automation), Outline (knowledge bases), and Keycloak (identity/auth).
Building Claude Code with Boris Cherny — The Pragmatic Engineer
Boris Cherny — creator and Head of Claude Code at Anthropic — sits down with Gergely Orosz for a 98-minute deep conversation covering Claude Code's origin story, the terminal-first design philosophy, how it handles 100K-file codebases, and where AI-assisted development is heading.
Mitchell Hashimoto's New Way of Writing Code – The Pragmatic Engineer
Mitchell Hashimoto — creator of Vagrant, Terraform, and co-founder of HashiCorp — shares his radically new approach to writing code with AI agents, covering his workflow philosophy, prompt engineering patterns, and how he achieves 10x productivity gains.