BYOB: Build Your Own Benchmark
The Emerging "Harness Engineering" Playbook
GPT-5.3-Codex and Claude Opus 4.6: More System Card Shenanigans
The Codex App Has Upended My Daily Workflow
Humans Welcome to Observe
Skills, Tools and MCPs - What’s The Difference?
The AI Manager's Schedule
On Joining OpenAI
10 AI Stories That Shaped 2025
