Agents Merge. Someone Still Has to Ship.
Creation runs at machine speed. Release engineering does not. GitHub agent-authored PRs went from 4M to 17M in six months. The bottleneck moved from review to release.
Read more →Boring Agents Ship: The Triage Lane Nobody Is Writing About
Most agent discourse is about coding agents. The agents quietly running in production right now are simpler, dumber, and more useful: stale-ticket sweepers, board monitors, three-line incident explainers, leadership briefs from a fixed template. Different species. Different shape. Already shipping.
Read more →Codex Hits 4M: Quality Is What's Left to Brag About
OpenAI publishes weekly active developers. Anthropic publishes annual recurring revenue. Each company brags about the metric it can defend. Codex went 600K to 4M in four months. The 'Claude Code is better' discourse is a quality argument because quality is what's left when scale goes the other way.
Read more →The Subscription Arbitrage Endgame
Anthropic tried technical blocks. Got their source leaked. Now they're shifting to billing enforcement. The four-month arc from hostile crackdown to 'use what you want, but pay for it.'
Read more →Claude Code Auto-Fix: The PR That Fixes Itself
Claude Code can now watch your PRs in the cloud, fix CI failures, and address reviewer comments while you're away. It's the logical next step after auto mode - and it raises the same trust questions, harder.
Read more →Claude Code Auto Mode: The Absent Human
Anthropic's new auto mode replaces manual permission prompts with an AI classifier. It's a clever solution to a real problem - but the problem it's solving is that the human in human-in-the-loop was never really there.
Read more →Channels: The Crab Eats the Lobster
Anthropic shipped Claude Code Channels - text your agent from Telegram. It's OpenClaw's core feature, rebuilt as a platform primitive. The absorption pattern completes its biggest cycle yet.
Read more →Autoresearch Became a Primitive
Eight days after Karpathy open-sourced autoresearch, the community ported the pattern to GPU kernels, security hardening, Apple Silicon, and agent optimization. The loop - one file, one metric, git as memory - turns out to be the interesting part.
Read more →Autoresearch: 700 Experiments While You Sleep
Karpathy's autoresearch gives an AI agent a training script, a GPU, and a git branch. It runs 100 experiments overnight, keeps what works, discards what doesn't. The human writes the prompt. The agent writes the code.
Read more →Amazon's AI Outages Escalated. So Did the Denial.
Two weeks after Kiro deleted a production environment, Amazon.com itself went down for 6 hours. 1,500 engineers are petitioning for Claude Code. The safeguards are arriving after the damage.
Read more →Your AI Tools Are the Attack Surface
Prompt injection through pull requests, GitHub Issues, and CI/CD pipelines is turning AI coding assistants into weapons against the developers who use them. The 2026 attack surface nobody's talking about.
Read more →Stupid and Industrious
A German general's 1933 framework for categorizing officers maps perfectly to engineers using AI. The most dangerous quadrant - stupid and industrious - is exactly what AI amplifies.
Read more →From Ralph Wiggum to /loop: The Absorption Continues
Claude Code shipped /loop - cron-based scheduled tasks. It's not Ralph Wiggum. It's what happens when the platform asks 'what's the simplest version of this pattern?'
Read more →Delete and Recreate: When AWS's AI Agent Went Rogue
Amazon's Kiro AI decided to delete and recreate a production environment, causing a 13-hour AWS outage. Amazon says it was human error. That framing is the problem.
Read more →The Neurodivergent Stack: Why Different Brains Built Tech, and Why Agents Need Them
ADHD, autism, and neurodivergence aren't bugs in the system. They're the reason the system exists. And the agentic age is about to prove it.
Read more →Your PM Tool Was Designed for Humans
Jira, Confluence, standups, sprint planning - all optimized for human coordination overhead. In an agent-native world, the bottleneck isn't status updates. It's whether the agents are unblocked.
Read more →Agent Teams: The Switch Got Flipped
Two weeks ago we found TeammateTool hiding in Claude Code's binary. Now it's official. Here's what changed, what didn't, and what the docs reveal about where multi-agent is heading.
Read more →When AI Isn't Fit for Purpose: Lessons from Salesforce's Agentforce Pivot
Salesforce quietly walked back autonomous AI agents to deterministic scripting. The pattern reveals when LLMs work - and when they don't.
Read more →Your Lobster Is Leaking
OpenClaw went from 0 to 111K GitHub stars in two months. It also went from 0 to hundreds of exposed instances with full credentials in Shodan. The security story nobody wants to hear.
Read more →The Lobster Grew a Face
When AI agents started posting on their own social network about shared context limit problems, I realized we're not building tools anymore. We're raising digital pets.
Read more →The Speedrun That Broke Open Source
AI tools that democratize code creation are DDoSing the review layer. Creation now runs at machine speed. Review remains human speed. The asymmetry is crushing maintainers.
Read more →Claude Code's Hidden Multi-Agent System
Anthropic built a full multi-agent orchestration system into Claude Code. It's feature-flagged off. The community found it anyway.
Read more →The Lobster That Outran Siri
People are buying Mac Minis to run an open-source AI assistant built by a retired iOS dev. Meanwhile Apple pays Google $1B/year because they still can't build a real AI.
Read more →From Beads to Tasks: Anthropic Productizes Agent Memory
Anthropic credits Steve Yegge's Beads as inspiration for Claude Code's new task system. The pattern-to-product cycle continues.
Read more →I Kept Writing About Broken Ads. Then We Built FameCake.
From diagnosing ad fraud to building a solution. Introducing FameCake: mobile-first billboard booking for everyday moments.
Read more →The Pin
A lookup table technique that improves search tool hit rates in autonomous loops. The detail that makes specs discoverable.
Read more →The Ralph Wiggum Playbook
The methodology behind autonomous coding loops. Three phases, five files, and the backpressure that makes it converge.
Read more →Anthropic's Walled Garden: The Claude Code Crackdown
Anthropic blocked third-party tools from using Claude subscriptions overnight. OpenCode, xAI, and power users caught in the crossfire. The era of subscription arbitrage is over.
Read more →Tailwind Lost 80% of Revenue. AI Didn't Replace the Developers.
75M monthly downloads. 80% revenue drop. 75% of engineers gone. AI didn't replace developers - it replaced the web as the interface layer. That's worse.
Read more →Claude Code 2.1: The Pain Points? Fixed.
Skills controllability, hooks limitations, plan mode friction - 2.1 addresses the documented pain points. Here's what changed and what's still missing.
Read more →Claude Code Hooks: Guardrails That Actually Work
Real footgun stories and the deterministic hooks that would've prevented them. From $30k API key leaks to nuked home directories.
Read more →Guardrails by Default: Why AI Coding's Next Evolution Isn't Smarter Models
Factory AI's Luke predicts the future isn't more powerful models - it's AI that enforces software engineering best practices by default. Here's why that matters more than you think.
Read more →The $0 SaaS Stack: Ship Fast, Pay Later
Convex, Vite, Clerk, shadcn, Cloudflare, Resend. A modern stack where every component has a generous free tier, agents do the heavy lifting, and you don't touch infrastructure until you have paying customers.
Read more →claude-launcher: Model Freedom for Claude Code
A CLI wrapper that lets you swap Claude Code's backend between Anthropic and OpenRouter with a single command. Pick any model, configure role-specific models, and switch between them instantly.
Read more →The Open Source Agentic Moment
Two major open source coding models dropped in 48 hours. Both target Claude Code compatibility. Both MIT licensed. The economics of agentic AI just changed.
Read more →Claude in Chrome: Close the Dev Loop Without Leaving Your Terminal
Claude Code can now control your actual Chrome browser. Not a headless session, not a fresh login - your Chrome, with your cookies and sessions. Build, test, and debug without context switching.
Read more →Gemini 3 Flash: The Model That Shouldn't Exist
Top 3 intelligence. Top 5 price. Top speed. Flash beats Pro on SWE-bench and changes the economics of agentic workflows.
Read more →Tether: Encrypted Dotfile Sync for Multi-Machine Developers
Stop manually copying .zshrc between machines. Tether syncs dotfiles and global packages with end-to-end encryption.
Read more →Three Ways to Build Deep Research with Claude
From 20 lines of shell to production apps. Anthropic renamed Claude Code SDK to Agent SDK because deep research is now a first-class use case.
Read more →Visual Verification: Making Agents Prove Their Work
Screenshots as source of truth, reference comparison to catch agent lies, and video capture for temporal bugs. How multimodal validation changes coding agent workflows.
Read more →Beads: Memory for Your Coding Agents
Steve Yegge's open-source framework gives coding agents session memory and task management. Four weeks old, hundreds of contributors, and already changing workflows.
Read more →claude-tools: A Plugin Marketplace for Claude Code
Six plugins that extend Claude Code with specialized external tools: Gemini for visual analysis, Codex for architecture thinking, Headless for browser automation, Mobile for native app testing, DNS for multi-provider management, and Miro for board reading.
Read more →Claude Code Gets Path-Specific Rules (Cursor Had This First)
Claude Code 2.0.64 adds .claude/rules/ with path matching. It's a welcome addition, but Cursor's had .cursor/rules/ for months. Here's the comparison.
Read more →Your Ad Budget Is Feeding Bots: Why the Future Is Physical
51% of web traffic is now bots - the first time machines exceeded humans. $238B wasted on fake impressions in 2024. Out-of-home is the fraud-proof alternative.
Read more →Your Website Is About to Become a Workflow
The human-facing web is dying. Zero-click searches, bot traffic exceeding humans, publishers losing 40%+ traffic. What comes next: an agentic web where sites are API endpoints, not destinations.
Read more →12 Factor Agents: Principles for AI That Actually Work
HumanLayer's 12-factor agents codifies what works in production AI: own your context, keep agents small, stay out of the dumb zone.
Read more →Ralph Wiggum: Autonomous Loops for Claude Code
The official Claude Code plugin that lets agents work autonomously for hours. When to use it, when not to, and the philosophy behind letting AI fail repeatedly until it succeeds.
Read more →Agent Harnesses: From DIY Patterns to Product
Anthropic's engineering team published patterns for long-running agents. These same patterns - progress tracking, feature lists, session protocols - are what products like SpecPilot must solve at scale.
Read more →From Single Model to Specialized Tooling: Adding React Grab to the Stack
My AI workflow evolved from 'Claude does everything' to specialized tools for each task. React Grab fills the UI extraction gap I didn't know I had.
Read more →The SDLC Is Collapsing Too
The PM/Eng split dissolved into product engineering. Now the traditional software development lifecycle is following suit as coding agents handle multi-hour tasks across planning, building, testing, and deployment.
Read more →Hybrid AI Workflows: Spawning Gemini from Claude Code
Claude Code for development, Gemini 3 Pro for visual analysis, research, and deep thinking. A slash command that routes tasks to the right model.
Read more →Skills Auto-Activation via Hooks (Does It Solve the Problem?)
Hooks-based skill activation solves context selection (which guidelines? which tools?) but not workflow orchestration. Both patterns have their place.
Read more →Claude Skills: The Controllability Problem
Skills are auto-invoked by Claude's judgment. For engineering workflows that need predictability, slash commands give you explicit control.
Read more →Isolating MCP Context in Claude Code with Slash Commands
How to use slash commands to keep specialized MCP tools isolated from your main conversation context.
Read more →DeepSeek-OCR: Compressing Text by 20x Using Vision
Converting text to images for 20x token compression. Interesting research or production-ready breakthrough? A critical look at the trade-offs.
Read more →Few-Shot Learning for Document Parsing: Training AI on Human Corrections
How I built a self-improving document parser that learns from corrections without fine-tuning. The pragmatic alternative to model training.
Read more →Cascading AI Pipelines: When One Model Feeds Another
Building a multi-stage AI content pipeline where each generation depends on the last. Lessons from generating thousands of hybrid creatures with resilient error handling.
Read more →Flutter Auto-Reload for Terminal Workflows
Building automatic hot reload for Flutter without an IDE using file watchers and Unix signals - for terminal-based development and AI coding tools.
Read more →