🔥 Asked Codex and Claude Code to each try their…

· · Aug. 30, 2026, 12:34 a.m.
Summary
This blog post discusses testing the capabilities of two AI models, Codex and Claude, in solving a complex text layout issue specific to Japanese vertical writing. It highlights the performance disparity between the two models, with Codex underperforming significantly compared to Fable's solution.
AUTHOR
Sponsored
Zulip logo Zulip
Organized team chat for people who take work seriously. Topic-based threading keeps conversations focused.
Try Zulip
Become a sponsor →