Why Codex works better than Claude Code for my production monolith
Sentiment Mix
Geography
Expert Signals
anophelon
author • 1 mention
Hacker News
source • 1 mention
AI-Generated Claims
Generated from linked receipts; click sources for full context.
Over the last year I mostly used Codex, but during the last month I tried Claude Code with Opus 4.6 and 4.7.
Supported by 1 story
These are my notes.This is not a benchmark.
Supported by 1 story
It is just my experience from daily use on one production codebase.
Supported by 1 story
For some medium-complexity tasks, I also ran both tools with the same prompts, but I did not try to make this a controlled evaluation.TL;DR: for my production Python monolith, I still prefer Codex.The codebase is a many-years-old Python backend.
Supported by 1 story
It has several architectural layers from different periods: a newer experimental DDD-ish style, older but still well-structured legacy code, and very old fragile spaghetti code.We usually do not rewrite old parts unless we have to.
Supported by 1 story
Related Events
Ask HN: Can you tell the difference between Claude Sonnet and Opus?
LLMs • 4/29/2026
Ask HN: Is it just me or is Claude Code getting worse?
LLMs • 4/29/2026
I tested ChatGPT vs Claude to build my Spotify playlists — one nailed it with much better songs - Tom's Guide
LLMs • 4/29/2026
Adobe integrates creative cloud tools into Claude with new AI connector - Social Samosa
LLMs • 4/29/2026
Anthropic's Champion Kit for engineers pushing Claude Code at their company
LLMs • 4/29/2026
Causality Chain
Preceded By