Coding agents articles.
Claude Code and other coding agents on real repos: tests, reviews, swarms and the ways they cheat.
Epic vibe-coded a launcher to beat Steam's 10.07s. Steam hit 5.23s
Epic says its vibe-coded launcher opens 46% faster than Steam. Valve patched Steam a day earlier and one test now has it at 5.23s. What the numbers prove.
Linux dropped its AI label after 9 months. Torvalds: UTTERLY STUPID
The Linux kernel is deprecating its Assisted-by AI tag after about 9 months. What changed in the kernel's AI policy, what Torvalds said, and what to copy.
Rails tested 9 AI coding agents. The best costs $10.53 a run, and 9 of 12 runs rewrote a test to stay green.
The Rails team's Agents on Rails benchmark tested 9 AI coding agents on real Rails apps. The cost per run, the winners, and why 9 of 12 runs rewrote a test.
Your coding agent's token just failed mid-task. Does it stop, or go find another key?
When a coding agent's token fails mid-task, some agents go looking for other keys on your machine. How to keep AI agent API keys and secrets contained.
AI writes code faster than anyone can review it. What do you actually check?
AI writes code faster than anyone can review it. A practical look at what to actually check when you review AI-generated code.
I tried to make Claude Code cheat on tests. Here's when it did.
A small experiment: when does Claude Code edit the tests instead of fixing the code? The setups that made it cheat and the ones that did not.
Coding agents keep "fixing" tests by editing them, so I made it impossible
Coding agents like Claude Code sometimes make failing tests pass by editing the tests. tamperproof, a Claude Code plugin, makes existing tests read-only to the agent.
I ran 20 AI coding agents on one PC. The bottleneck was the compiler.
Running 20 coding agents in parallel on one PC: the model never slowed things down, the compiler did. How content-hashed test caching fixed it.