Themata.AI
Themata.AI

Popular tags:

#developer-tools#ai-agents#discussion#trending#llms#ai-ethics#claude#code-generation#ai-safety#openai

AI is changing the world. Don't stay behind. Clear summaries, community insight, delivered without the noise. Subscribe to never miss a beat.

© 2026 Themata.AI • All Rights Reserved

Archive

|

Topics

|

Privacy

|

Cookies

|

Contact
openaicodexllmsdeveloper-tools

GPT-5.3-Codex being routed to GPT-5.2

GPT-5.3-Codex being routed to GPT-5.2 · Issue #11189 · openai/codex

github.com

February 11, 2026

1 min read

🔥🔥🔥🔥🔥

47/100

Summary

GPT-5.3-Codex is being routed to GPT-5.2 in Codex CLI version 0.99.0-alpha.10. The user is subscribed to ChatGPT Pro and is operating on a Darwin 25.2.0 arm64 arm platform using the Ghostt terminal emulator.

Key Takeaways

  • The user is experiencing an issue where the Codex CLI is set to use gpt-5.3-codex, but the output indicates it is using gpt-5.2-2025-12-11.
  • The problem occurs despite both the config.toml and TUI being configured for gpt-5.3-codex.
  • The issue can be reproduced by running specific commands in the Codex CLI environment.
  • The expected behavior is for the system to utilize gpt-5.3-codex instead of gpt-5.2.
Read original article

Coverage & discussions

Hacker News · github.com

GPT-5.3-Codex being routed to GPT-5.2 ↗

Community discussions

Hacker News discussion ↗

Historical count: 5 · 5 saved in sample · Historical sample

Analysis ready

Community Sentiment

Negative

Positives

  • The GPT-5.3-codex model is recognized as OpenAI's most cyber-capable reasoning model, indicating significant advancements in AI's ability to assist in cyber defense applications.

Concerns

  • Users are frustrated that they are being routed to a less capable model without notification, raising concerns about transparency and the value of their subscription.
  • The requirement for identity verification to access the powerful GPT-5.3-codex model creates barriers that could deter users from utilizing advanced AI capabilities.
  • Concerns about the potential misuse of the GPT-5.3-codex model highlight the ongoing ethical dilemmas surrounding powerful AI technologies and their regulation.
  • The slow response speed of the GPT-5.3-codex in the Codex CLI suggests performance issues that could hinder user experience and application effectiveness.

Related Articles

Native Bedrock Codex GPT-5.6 Sol lacks explicit cache controls, producing high cache-write spend · Issue #37674 · openai/codex

Codex on AWS bedrock bug causing 10x charges

Aug 21, 2026

Codex Desktop continuously generates Crashpad pending dumps, growing without any limit: +5GB per day at least · Issue #25921 · openai/codex

Codex Desktop continuously generates Crashpad pending dumps

Oct 17, 2026

OpenAI restores 5-hour Codex and Work limits for ChatGPT Plus users - 9to5Mac

OpenAI restores 5-hour Codex and Work limits for ChatGPT Plus users

Aug 25, 2026

Pricing | OpenAI API

OpenAI: GPT 5.6 Sol price reduction (until at least Nov 21)

Aug 24, 2026

Codex in ChatGPT | AI Coding Agents for Software Engineering

ChatGPT Desktop (Codex Desktop) for Linux

Aug 13, 2026