Interview with Andrew Ambrosino, project lead for OpenAI's Codex, discussing its history, integration with ChatGPT, Computer Use, and user trust.
Analyzes OpenAI's claim that Codex helped Asana migrate from Enzyme to React Testing Library in 2 weeks, comparing testing frameworks and questioning feasibility.
OpenAI's Computer History feature for ChatGPT and Codex on Mac turns actions into Markdown memory files for better context and continuity.
A developer compares AI coding tools by having Codex with GPT-5.6 Sol Ultra build a raccoon heist game, fixing bugs and sharing results.
An opinionated guide comparing AI tools like ChatGPT and Claude, focusing on agentic systems and computer access modes.
A developer creates a custom Codex Desktop pet called Pedalican, a pelican on a bicycle, using GPT-5.6 and image generation.
How to use AI coding agents like Claude Code and Codex for deterministic data engineering, ensuring reproducibility and trust.
A developer's reflections on using AI agents for coding, testing, and bug fixing, including a fabricated bug reproduction story.
Explains how to build robust agent workflows by coordinating with state ownership instead of relying on timing, using a Codex migration example.
Experiment using AI agents to interact with web apps, find defects, and report via GitHub issues and PRs for automated interactive review.
Google launches Antigravity 2.0, a redesigned AI IDE that removes traditional IDE features for a conversational agent interface.
Guide to exporting and using Xcode 27's official Agent Skills in third-party IDEs like Claude, Codex, and Cursor.
A quote from Romain Huet confirming OpenAI won't release a separate GPT-5.5-Codex model, as coding capabilities are unified.
GPT-5.5 is released via Codex; a new LLM plugin uses the semi-official backdoor API to access it through OpenAI subscriptions.
Release of llm-openai-via-codex 0.1a0, enabling OpenAI model access via Codex CLI credentials.
Release of llm-openai-via-codex 0.1a0, a plugin to access OpenAI models via Codex CLI credentials.
OpenAI offers 6 months of ChatGPT Pro with Codex to core maintainers of significant open source projects, following a similar move by Anthropic.
OpenAI announces GPT-5.4 and GPT-5.4-Pro models with enhanced coding, document creation, and a 1M token context window.
Managing multiple AI coding agents in Xcode by isolating their DerivedData folders to prevent build conflicts and maintain a clean workspace.
OpenAI's Codex Spark, a fast coding model, runs on Cerebras' WSE-3 chip, marking a shift in AI inference hardware for low-latency tasks.
