PROJECT 4
×00

The Project 4 Blog

Anthropic To Add Watermarks To All Claude-Generated Content

Industry · Working with AI

As of August 2, 2026 Anthropic will be watermarking everything that Claude generates for you.

Read article

Physical AI: When the Failure Mode Has Mass

Industry · Working with AI

A model in a physical form changes what a mistake costs. What actually changed in robotics and why a 99 percent success rate counts as a failure.

Read article

Prompt Injection Awareness

Security · Working with AI

As of today, a model can't reliably distingush what your instructions are compared to a hidden prompt injected into some other content it has loaded in. Local coding agents get hit the hardest.

Read article

Stop Shipping AI-Looking Websites

Design · Working with AI

There are some clear indicators to the majority of AI-generated websites. The fix is direction: a real spec, a plan, and your efforts precisely broken down.

Read article

Five Ways to Keep Your AI Agent From Shipping Insecure Code

Part 3 · Beyond the Prompt

AI agents write code fast, and they write insecure code with exactly the same confidence as secure code. Five practices worth building into your workflow.

Read article

A Bigger Context Window Won't Save You

Part 2 · Beyond the Prompt

When an AI agent keeps getting your codebase wrong, the answer is to decide what it gets to see. A smarter model or a longer context window rarely helps.

Read article

Your AI Coding Agent Doesn't Need a Better Prompt

Part 1 · Beyond the Prompt

The honeymoon with “vibe coding” ends the moment you point an agent at a messy codebase. What replaces it is a discipline you have to practice.

Read article

Ten Things I Wish I Knew When I Started Coding With Agents

Lessons · Working with AI

When I started with AI, I thought the hardest part would be writing prompts to get what I wanted back. Most of what I thought at that time turned out to be wrong.

Read article

Have a Working Knowledge of Everything You Throw at the AI

Industry · Working with AI

Try to always have basic knowledge of what you are handing to an AI agent. Drifting away from this premise will almost always cost you in the long run.

Read article

Loop Engineering

Part 3 · The Agent Stack

The people who build the most-used coding agents stopped hand-prompting. A loop that prompts, checks, remembers, and re-runs the agent for you is the next iteration.

Read article

The AI Bottleneck Moved From Chips to Power

Industry · Working with AI

For 2 years silicon was the most in-demand resource, but now it is electricity. Data-center power demand is set to double by 2030 and just about 75 US projects were canceled for the lack of it.

Read article

Why Vibe Designing Will Outlast Vibe Coding

Design · Working with AI

Vibe designing lasts where unguided vibe coding did not. The reason is a faster first loop that lets taste lead, plus the same structure that makes any generation trustworthy. And the checks the eye can never run on its own.

Read article

Build a Team of Specialists: Subagents in Claude Code

Agents · Working with AI

Three hours in, your context window is full. A subagent hands the side task to a separate instance with its own context, tools, and model, and returns only the result. How to build narrow specialists, four to steal, and why it ports to Codex.

Read article

Running a Team of Agents Without the Chaos

Part 2 · The Agent Stack

You've gone from conductor to orchestrator. The bottleneck moved from the agent's capability to coordination. Here's how to run parallel agents without quietly corrupting your codebase.

Read article

The AI Code Review Gauntlet

Part 1 · The Agent Stack

AI code fails in predictable, well-documented ways. This is the review gauntlet: five failure classes and the fast tells that catch the most damage per minute of attention.

Read article

How CSS Specificity and the Cascade Work

Part 3 · Frontend Fundamentals

Specificity is step four, not the whole story, and it never carries the way people think. How the cascade actually picks a winner, and why :where() and @layer end the !important arms race.

Read article

Semantic HTML and Focus Order for Keyboard Accessibility

Part 2 · Frontend Fundamentals

Ask an agent for a dropdown and you usually get one the keyboard can't reach. The div that should be a button, the missing focus ring, and the tab order that fights the markup.

Read article

How to Choose Between Flex or Grid

Part 1 · Frontend Fundamentals

Forget one dimension versus two. The question that actually decides it is who sizes the items, the content or you, plus the five gotchas agents get wrong most.

Read article