A naukri.com initiative
VentureBeat
2d
275
Image Credit: VentureBeat
OpenAI launches research preview of Codex AI software engineering agent for developers — with parallel tasking
- OpenAI has launched Codex AI software engineering agent as a research preview to compete with other AI coding tools like Windsurf and Cursor.
- Unlike the previous Codex model, the new version is a cloud-based AI software engineering agent capable of executing multiple development tasks in parallel.
- The new Codex is available for ChatGPT Pro, Enterprise, and Team users, with support for Plus and Edu users expected in the future.
- It marks a significant advancement from the original Codex model, which focused on code generation and completion.
- The new Codex can write features, fix bugs, answer codebase-specific questions, run tests, and propose pull requests in a secure cloud sandbox.
- OpenAI envisions Codex as a tool that can operate autonomously to accomplish substantial work by interacting with the real world.
- The Codex-1 SWE agent outperforms OpenAI's latest reasoning models on internal SWE tasks.
- External use cases include Cisco, Temporal, Superhuman, and Kodiak utilizing Codex for various engineering tasks.
- Codex executes tasks in an air-gapped environment with human review to ensure secure operation, making it more than just a model API.
- OpenAI has launched Codex CLI for local development with updated pricing plans and a free rollout period.
Read Full Article
16 Likes
For uninterrupted reading, download the app