Get the latest tech news
OpenAI’s Codex is part of a new cohort of agentic coding tools
The new crop of vibe coding tools can do more with less supervision, but reliability concerns linger.
Last Friday, OpenAI introduced a new coding system called Codex, designed to perform complex programming tasks from natural language commands. “In the beginning, people just wrote code by pressing every single keystroke,” explains Kilian Lieret, a Princeton researcher and member of the SWE-Agent team. Arguably the best measure of agentic programming progress is the SWE-Bench leaderboards, where developers can test their models against a set of unresolved issues from open GitHub repositories.
Or read this on TechCrunch
