AI

Addendum to o3 and o4-mini system card: Codex

OpenAI has released an addendum to its o3 and o4-mini system cards, specifically for Codex. Codex is a cloud-based coding agent powered by codex-1, a version of OpenAI's o3 model optimized for software engineering tasks. The model was trained using reinforcement learning on real-world coding tasks in various environments. This allows Codex to generate code that closely mirrors human style and adheres precisely to instructions. It also iteratively runs tests until passing resu
OpenAI has released an addendum to its o3 and o4-mini system cards, specifically for Codex. Codex is a cloud-based coding agent powered by codex-1, a version of OpenAI's o3 model optimized for software engineering tasks. The model was trained using reinforcement learning on real-world coding tasks in various environments. This allows Codex to generate code that closely mirrors human style and adheres precisely to instructions. It also iteratively runs tests until passing results are achieved. --- Why it matters: This matters to AI engineers because it provides a new tool for automating software engineering tasks, potentially increasing productivity and efficiency. The ability of Codex to mirror human coding style and adhere to instructions could also improve the quality of generated code. Source: https://openai.com/index/o3-o4-mini-codex-system-card-addendum

This article was originally published at: https://openai.com/index/o3-o4-mini-codex-system-card-addendum