Dev slams OpenAI Codex as buggy and slow, says Claude Code pulls ahead
lyraxana · x · 2026-10-05
A developer argues Anthropic now has better models, better limits, and a much better coding experience with Claude Code, while OpenAI's Codex keeps getting worse — buggy, slow, and bloated with features until it became 'like a curse.' The author says what happened at OpenAI in recent weeks needs to be studied and someone should take responsibility.
More from coding & agent
- GLM vs Qwen tool calling differences force separate handlers in Codex proxy — TheZachMueller · 2026-10-05
- Why running third-party models in Codex needs a tool-calling proxy layer — TheZachMueller · 2026-10-05
- Dev says nearly all his web searches now run through personal agents as web goes headless — illscience · 2026-10-05
- RelayDesk connects Claude to your own computers and VMs via MCP — whateverxp · 2026-10-05
- Musk amplifies "zero human company" run by a Grok bot as CEO — elonmusk · 2026-10-05
- The AI Checkout Demo Everyone Wants: Agent Retries Without Double-Charging — HaktanSuren · 2026-10-05