AI Thoughts & Opinions

Opus 4.6 and Codex 5.3 launched on the same day, but this time nobody’s looking at benchmarks. The AI coding assistant race has shifted from ‘who’s stronger’ to ‘who’s more usable’ — we’ve officially entered an era where system experience matters more than model capability.

A deep dive into Paul Graham’s latest essay: writing that sounds good is more likely to be correct. It sounds absurd, but his ‘shaking the box’ metaphor explains it perfectly.