OpenAI on Friday, May 16, introduced a new AI tool called Codex that is designed to handle multiple software engineering-related tasks at the same time, from generating code for new features to answering questions about a user’s codebase, fixing bugs, and suggesting pull requests for code review
The cloud-based, AI agent-driven coding tool runs these tasks in its own cloud sandbox environment that has been preloaded with a user’s code repository.
Codex has been released under research preview. However, all ChatGPT Pro, Enterprise, and Team users have access to the AI coding tool. “Users will have generous access at no additional cost for the coming weeks so you can explore what Codex can do, after which we’ll roll out rate-limited access and flexible pricing options that let you purchase additional usage on-demand,” OpenAI said in a blog post.
ChatGPT Plus and Edu customers will be given access at a later date, the Microsoft-backed AI startup added.
https://platform.twitter.com/widgets.js
OpenAI’s latest offering comes at a time when AI is poised to disrupt the software engineering sector, raising widespread fears of job displacement. Microsoft CEO Satya Nadella recently said that 30 per cent of the company’s code is now AI-generated. A few weeks later, the tech giant announced it is laying off 6,000 employees or 3 per cent of its workforce, with programmers reportedly being impacted the most.
“It still remains essential for users to manually review and validate all agent-generated code before integration and execution,” OpenAI noted in its Codex announcement blog post.
What is Codex?
With Codex, developers can delegate simple programming tasks to an AI agent. It has its own unique interface that can be accessed from the side bar in the ChatGPT web app.
Codex is powered by codex-1, an AI model that is a variation of OpenAI’s o3 reasoning model. Except that codex-1 has been specifically trained on a wide range of real-world coding tasks to analyse and generate code “that closely mirrors human style and PR preferences, adheres precisely to instructions.”
Its outputs have further been fine-tuned using reinforcement learning so that codex-1 can “iteratively run tests until it receives a passing result.” In terms of performance and accuracy, OpenAI said that codex-1 fared better than its o3 AI model when evaluated on its internal SWE benchmark as well as the company’s human-validated version of it (SWE-bench Verified).
How does Codex work?
Codex can read and edit files as well as run commands including test harnesses, linters, and type checkers. It typically takes anywhere between one minute to 30 minutes to complete a task depending on the difficulty level, as per OpenAI.
The AI coding agent performs each task in a distinct, isolated environment that is preloaded with the user’s codebase serving as context. “Like human developers, Codex agents perform best when provided with configured dev environments, reliable testing setups, and clear documentation,” OpenAI said.
Users can make Codex work more effectively for them by including AGENTS.md files placed within their 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,” OpenAI further said.
Another unique feature of Codex is that it shows its thinking and work with every step as it goes about completing the task(s). In the past, several developers have pointed out that AI coding agents produce coding scripts that do not follow standards and are difficult to debug.
“Codex provides verifiable evidence of its actions through citations of terminal logs and test outputs, allowing you to trace each step taken during task completion,” OpenAI said.
Once Codex completes a task, it commits its changes in its environment. However, users can also review the results, request further revisions, open a GitHub pull request, or directly make changes in the local development environment.
How to use Codex? What are its use cases?
In order for Codex to start generating code, users need to enter a prompt and click on ‘code’. If they want the AI coding agents to answer questions or provide suggestions, then users need to select the ‘ask’ option before submitting the prompt.
When OpenAI opened up early access to Codex for external partners, they used the AI coding agent tool to accelerate feature development, debug issues, write and execute tests, and refactor large codebases. Another early tester used Codes to speed up small but repetitive tasks like improving test coverage and fixing integration failures.”
It can also be used to write debugging tools and help developers understand unfamiliar parts of the codebase by surfacing relevant context and past changes.
OpenAI developers are also using Codex internally for refactoring, renaming, and writing tests as well as scaffolding new features, wiring components, fixing bugs, and drafting documentation.
“Based on learnings from early testers, we recommend assigning well-scoped tasks to multiple agents simultaneously, and experimenting with different types of tasks and prompts to explore the model’s capabilities effectively,” the company said.
What is the difference between Codex and Codex CLI?
In April this year, OpenAI launched another AI coding agent tool called Codex CLI. It is said to be an open-source, command-line tool capable of reading, modifying, and running code locally on a user’s terminal.
The coding agent integrates OpenAI’s models with the client’s command-line interface (CLI) used to run programmes, manage files, and more.
Codex CLI is powered by OpenAI’s latest o4-mini model by default. However, users can choose their preferred OpenAI model via the Responses API option. Codex CLI can only run on macOS and Linux systems for now, with support for Windows still in the experimental stage.
In Friday’s blog post, OpenAI also announced updates to Codex CLI. A smaller version of codex-1 is coming to Codex CLI. “It’s available now as the default model in Codex CLI and in the API as codex-mini-latest,” OpenAI said.
The company has also simplified the developer log-in process for Codex CLI. Instead of having to manually generate and configure an API token, developers can now use their ChatGPT account to sign into Codex CLI and select the API organisation they want to use. “Plus and Pro users who sign in to Codex CLI with ChatGPT can also begin redeeming $5 and $50 in free API credits, respectively, later today for the next 30 days,” OpenAI said.
Amjad Masad, the CEO at Replit, called the incident “unacceptable and should never be possible”. (Image: Unsplash) 
Share
