OpenAI CODEX Features: Taking ChatGPT to the next level, Sam Altman-backed OpenAI has launched a new feature called 'CODEX', a cloud-based software engineering agent that can work on many tasks in parallel. This new feature is equipped to perform multiple tasks like writing features, answering questions about your codebase, fixing bugs, and proposing pull requests for review.
How Does Codex Work?
Codex can be accessed through the sidebar in ChatGPT. Users can assign new task coding tasks by typing a prompt and clicking "Code".
If you want to ask Codex a question about your codebase, click "Ask". Each task is processed independently in a separate, isolated environment preloaded with your codebase. Codex can read and edit files, as well as run commands including test harnesses, linters, and type checkers, as per the main release.
The timeframe for completing tasks at CODEX is generally around 1 to 30 minutes, based on the complexity. Users can monitor progress on a real-time basis.
Once the task is completed, CODEX commits its changes in its environment. This feature provides verifiable evidence of its actions through citations of terminal logs and test outputs, allowing you to trace each step taken during task completion.
Also, you can then review the results, request further revisions, open a GitHub pull request, or directly integrate the changes into your local environment. In the product, you can configure the Codex environment to match your real development environment as closely as possible, OpenAI said.
Additionally, on ChatGPT, Codex can be guided by AGENTS.md files placed within your repository. These are text files, akin to README.md, where you can inform Codex how to navigate your codebase, which commands to run for testing, and how best to adhere to your project's standard practices. Like human developers, Codex agents perform best when provided with configured dev environments, reliable testing setups, and clear documentation.
On coding evaluations and internal benchmarks, codex-1 shows strong performance even without AGENTS.md files or custom scaffolding, it said.
CODEX is released in-line with OpenAI's iterative deployment strategy.
"We prioritized security and transparency when designing Codex so users can verify its outputs - a safeguard that grows increasingly more important as AI models handle more complex coding tasks independently and safety considerations evolve. Users can check Codex's work through citations, terminal logs and test results," OpenAI said in a statement.
The statement highlighted that when uncertain or faced with test failures, the Codex agent explicitly communicates these issues, enabling users to make informed decisions about how to proceed. It still remains essential for users to manually review and validate all agent-generated code before integration and execution.
Click it and Unblock the Notifications
Sign in with Google