Tag
从编程智能体产品线交付的角度评论认为，Anthropic 已领先 OpenAI 两个身位，OpenAI Codex 经过数月迭代后用户体验变得过度防御、过度思考和过度工程化。
The author shares their experience of struggling to build a compiler with OpenAI Codex but finding success with Claude AI.
An experiment where the author used various AI models like Claude and Codex to port the game Prince of Persia from Apple II assembly to C#, demonstrating the progress in frontier models for code generation.
A tweet announces that Cursor's new update surpasses OpenAI Codex and Claude Code by solving context decay, urging viewers to watch for more details.
An interview with Thibault, head of OpenAI's Codex team, discussing Codex's development, the choice of Rust for its core, open-source strategy, and shifts in engineering practices at OpenAI.
A researcher uses OpenAI's Codex and ChatGPT to accelerate the discovery of new antimicrobial molecules by treating biology as information and leveraging AI to search vast datasets for functional patterns.
The article describes how MIT graduate student Beatriz Yankelevich used GPT-5.6 Sol with Codex to automate quantum computing experiments, saving time and enabling more focus on analysis and design.
This guide provides a step-by-step method to use Claude Code with the OpenAI Codex plugin and a 3-model workflow involving GPT-5.6 variants to reduce token consumption by at least 60% and avoid usage limits.
Asana used OpenAI Codex to remove the outdated Enzyme testing system in two weeks, completing a task estimated to take five years and saving approximately $6 million in costs.
The Autoresearch open-source project ports Karpathy's autoresearch approach to Claude Code, OpenCode, and Codex, letting AI agents automatically loop through code changes, run validation, and roll back based on goals and quantitative metrics. It provides 14 subcommands and 9 safety hooks.
A user reports reproducing a Codex Desktop behavior where existing sessions continue processing for up to 17 hours after usage limits hit zero, raising questions about how in-flight tasks are governed.
Cognizant hosted its first-ever OpenAI Codex Hackathon with 10,000 associates across six Indian cities, aiming to build AI fluency and translate skills into enterprise solutions.
The article argues that OpenClaw, an open-source AI coding agent, is declining or dead, pointing to its creator Peter Steinberger's move to OpenAI, and the rapid development of competing tools like Anthropic's Claude Code and OpenAI's Codex.
Aletheia is an open-source agent loop designed for investigating questions where answers cannot be easily verified, such as vendor credibility or financial health. It maintains an explicit belief state, chooses searches to maximize information gain, and can stop without forcing a conclusion when evidence is insufficient.
A new paper on OpenAI Codex reveals agentic AI usage grew over fivefold in the first half of 2026, with adoption expanding beyond software developers, indicating AI workflows may surpass chatbots.
An in-depth guide to loop engineering for AI coding agents, explaining how to build automated loops that repeatedly prompt agents, verify results, and avoid runaway costs, illustrated with a case study of one engineer shipping 259 PRs in a month.
OpenAI Codex is now free, but even more surprising is that local open-source models can achieve AI Agent performance close to the cloud, demonstrating scenarios like fixing games and developing web games without requiring API keys or internet.
Vercel released HarnessAgent in the Canary version of AI SDK 7, providing a unified API to switch between multiple AI agent runtime environments, simplifying development workflow.
A comprehensive list of core team members from three AI Agent development teams – OpenAI Codex, Claude Code, and Manus – covering leadership, API, ecosystem, security, and more, for readers interested in Agent development trends.