"OpenAI has released , a version of optimized for complex software engineering tasks such as large-scale code refactoring and extended code review workflows. Purpose-built for the Codex CLI, IDE extension, and cloud environment, the model can operate autonomously for more than seven hours to deliver working solutions without human intervention. It is now the default in Codex's cloud service and available wherever developers use Codex."
"A key feature of GPT-5-Codex is adaptive reasoning, which adjusts reasoning time based on task complexity. The model supports both interactive pairing with developers for smaller, well-defined tasks and persistent execution on extended refactoring work. OpenAI notes that while responses are faster in chat-style interactions, the model can allocate additional cycles to handle larger, multi-file code changes. OpenAI employee usage data suggests efficiency gains in how the model allocates computation."
OpenAI released GPT-5-Codex, a model optimized for complex software engineering tasks such as large-scale code refactoring and extended code review workflows. The model is purpose-built for the Codex CLI, IDE extension, and cloud environment and can operate autonomously for more than seven hours to deliver working solutions without human intervention. GPT-5-Codex uses adaptive reasoning to adjust computation based on task complexity, supporting interactive pairing for small tasks and persistent execution for extended refactors. Internal usage data shows major token efficiency on simple requests and greater compute investment for the hardest requests. Evaluations show higher refactoring accuracy and improved code-review capabilities, including repository navigation, dependency analysis, and test execution.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]