A collection of interesting and thought-provoking posts and articles I've run across recently. I don't necessarily agree with all the opinions presented, but they are worth reflecting on.
Several design choices suggest optimization toward passing tests rather than building general abstractions like a human would.
The Claude C Compiler: What It Reveals About the Future of Software
Patterns for getting the best results out of coding agents like Claude Code and OpenAI Codex.
Agentic Engineering Patterns
Between Dec 21st, 2025 and Feb 9th, 2026 a prompt injection vulnerability in Cline’s (now removed) Claude Issue Triage workflow allowed any attacker with a GitHub account to compromise production Cline releases on both the Visual Studio Code Marketplace and OpenVSX and publish malware to millions of developers! Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager
We’re not going to outread the machines. We need to outthink them—upstream, where the decisions actually matter.
Ultimately, if agents can handle the code just fine, what does it matter if we can read it or not?
How to Kill the Code Review