GPT‑5-Codex Lands in Codex Tools, API Coming Soon, With Big Push on Code Review

OpenAI unveiled GPT‑5-Codex for coding tasks, integrated into VS Code, Codex CLI, and Codex Cloud, with API access coming later. Codex Cloud adds automated GitHub code reviews leveraging temporary containers. Early signals show improved refactoring and fewer low‑value comments, but some tool-usage gaps and rough edges remain.

Key Points

• GPT‑5-Codex is live in OpenAI’s coding tools (VS Code extension, Codex CLI, Codex Cloud) but not yet in the API.
• Codex Cloud now offers automated GitHub code reviews using ephemeral containers.
• Model upgrades focus on code review, dynamic compute time, refactoring quality, mobile-friendly output, and more focused comments.
• The GPT‑5-Codex system prompt is shorter than prior models’ prompts in Codex CLI.
• Early testing and reviews show promise but also shortcomings, such as poor use of the CLI’s search tool and imperfect creative outputs.

Sentiment

Neutral to mildly skeptical, mostly humorous; broadly aligned with the article’s observations with no substantive pushback.

In Agreement

• Clarification that the “comments” improvement refers to code review comments, aligning with OpenAI’s description.
• Agreement that the pelican SVG example was weak, reinforcing the article’s point that the model still has rough edges.
• Implicit acknowledgment (via jokes) that speed may be a notable strength of the new tooling.

Opposed

• Initial misinterpretation that the model reduces unimportant comments within source code rather than in code reviews, indicating confusion about the claim.
• Light skepticism implied by jokes that speed may be emphasized even when output quality is questionable.