#codex
Codex: 23 AI articles covering codex news, analysis, and research
Articles
OpenAI Is Developing a 'Persistent' AI Agentโญ9
OpenAI is developing a persistent Codex AI agent that works autonomously until turned off, enabling longer, self-directed coding workflows.
โThe world seems to be readyโ: An interview with OpenAIโs headโญ8
OpenAI's head of product discusses ChatGPT Work, AI agents for professionals, winning skeptics, and the cost of intelligence in this exclusive interview.
Running Codex as a Headless Agentโญ10
Learn how to run Codex as a headless agent in automation workflows, using a Python process and HTML digest case study for repeatable tasks.
ChatGPT Can Now Send Texts for You with New Apple Messages Plug-Inโญ8
ChatGPT's new Apple Messages plug-in lets you draft, send, and analyze texts, boosting messaging efficiency, though privacy concerns remain.
IBM and OpenAI Forge Strategic Partnership to Accelerateโญ9
IBM and OpenAI partner to accelerate enterprise AI adoption, combining IBM's consulting network with OpenAI's models to drive real-world business transformation...
OpenAI Launches ChatGPT Desktop App for Linux, Closing theโญ8
OpenAI launches ChatGPT desktop app for Linux, expanding access to ChatGPT and Codex across major distros like Ubuntu, Debian, and Fedora.
Microsoftโs SkillOpt Shows Optimized Agent Skill Artifactsโญ8
Microsoft's SkillOpt optimizes AI agent skills via text-space editing without model retraining, enabling efficient cross-model and cross-harness transfer of per...
Meta Debuts AI Coding Agent Muse: How It Stacks Up Againstโญ9
Meta's Muse AI coding agent debuts, rivaling Claude Code and Codex in code generation, debugging, and workflow integration with unique legacy code handling.
Supabase Releases Evals: An Open-Source Benchmark for Claudeโญ7
Supabase Evals is an open-source benchmark testing AI agents like Claude Code and Codex on real database tasks, security fixes, and edge functions.
DeepSeek Unveils DeepSeek-V4-Flash-0731: Major Agentic andโญ8
DeepSeek launches V4-Flash-0731 with DSpark speculative decoding and Responses API, boosting agentic workflows and coding speed.
