Tag
All content about Codex, organized for fast scanning.
OpenAI has introduced several enhancements to Codex, including an Ultrafast tier for faster code generation, now capable of generating up to 300 tokens per second. The platform has also expanded its capabilities with a one-million-token context window and improved installation processes for Arch Linux users. Additionally, new features like voice integration aim to facilitate hands-free workflows, although users have raised concerns about support and reliability.
OpenAI has just rolled out Ultrafast for Astra, promising up to 8x faster code generation in Codex than Standard. It can hit 300 tokens per second and pair with WebSocket mode in the Responses API. Enterprise and Pro 500 get access, with GPT-6.1 Sol support coming soon.
OpenAI’s Codex app is now easier to install on Arch Linux, removing prior workarounds. A new terminal script sets up a signed OpenAI repo, installs the ChatGPT desktop app, and runs a full system upgrade before prompting you to sign in.
OpenAI has just rolled out GPT-6 Astra, bringing the model to Pro, Enterprise, and Business Premium users across ChatGPT Work, Codex, and the API. Plus and Business access may take several days, fueling excitement—and complaints—on X.
Codex now supports a 1M-token context window for ChatGPT account usage, expanding beyond API-key-only access. The opt-in GPT-5.6 Sol setting can retain far more code and history, but users warn it may burn through usage faster.
OpenAI has outlined Voice in Codex workflows that go beyond dictation, from brainstorming into Linear tickets to coordinating multiple Codex sessions. Users also flagged gaps like Linux support, push-to-talk, reliability issues, and the need for stronger oversight logs.
OpenAI is rolling out pricing and speed updates for the GPT-5.6 lineup, including 80% lower Luna prices and 20% lower Terra rates. GPT-5.6 Sol gets faster /fast mode, while auto-approve “review for me” is now ~10x cheaper using Luna.
With the launch of the new ChatGPT desktop app, OpenAI is folding Codex into a dedicated workspace alongside a revamped browser, faster Computer Use, and a new ChatGPT Work Chrome extension. Sites also enters beta for Plus and Pro, while users ask about Windows, Linux, and existing workflows.
xAI appears to be adding a new /goal command to Grok Build, aimed at long-running autonomous tasks using rounds of subagents to implement and verify work. The move echoes recent goal-based agent workflows in OpenAI Codex and similar tools.
Codex appears to be gaining a seamless handoff feature, letting a thread move from a laptop to a remote host and back later. Guinness Chen says the repo’s code and git state transfer too, combining local dev ergonomics with remote compute.
OpenAI Codex lead Thibault Sottiaux reminded developers that the Codex app, CLI, and SDK can work with “any open source model,” not just OpenAI’s.
OpenAI is rolling out more Codex features across the EEA, UK, and Switzerland this week, including Computer use, the Chrome extension, memory, and Chronicle. Users welcomed the news but raised questions about platform support, limits, and capacity.
OpenAI’s Codex is leaning further into autonomous agents, with a new /goal flow that can infer tasks from user intent. Early users tout multi-thread coordination and long-running monitoring, while others push for tighter controls, better metrics, and improved reliability.
OpenAI has just rolled out a new “Developer mode” for Codex browser use, enabling Chrome DevTools Protocol access to profile JS performance and inspect console, network, and page state. Settings flag “Elevated risk,” warning full CDP access can expose sensitive browser internals.
A post from Tibo Sottiaux suggests Codex can run inside your own apps via Python SDK and CLI installs. Replies spotlight demand for Java/JS options and operational details like limits and login issues. A screenshot claims usage bills against ChatGPT subscription quota.
OpenAI has just rolled out Codex “Sites,” bringing a new way to turn work and ideas into interactive websites or apps shared by URL. It’s launching first for Business and Enterprise users, as developers debate where it fits and how it handles security, auth, and scale.
OpenAI has just rolled out general availability for its frontier models and Codex on AWS. The move lets enterprises tap existing Bedrock security, compliance, and governance workflows—though some users say the models weren’t yet showing up in catalogs.
OpenAI is set to sunset GPT-5.2 and GPT-5.3-Codex in Codex on June 2 for users signed in with a ChatGPT account. GPT-5.5 will become the default frontier model on free plans, while older options remain available via the API.
Zed has just rolled out ChatGPT subscription sign-in for its agent, matching Codex’s usage and rate limits. The company says you can also connect via ACP, Codex CLI, or an API key, with fast mode support “coming soon.”
OpenAI has just rolled out a Codex preview inside the ChatGPT mobile app, letting you monitor work, review outputs, and approve next steps from iOS and Android. Early reactions are mixed, with some users praising the “mission control” feel and others reporting pairing bugs.
With the promotion, OpenAI is looking to make Codex the default AI coding tool inside more companies. Sam Altman says switchers get two months free over the next 30 days, but reactions are split on whether it’s enough to drive adoption.
Notion has just rolled out its External Agents API, bringing third-party and custom agents directly into your workspace. The company says partners like Claude, OpenAI Codex, Cursor, and more will work out of the box, with a waitlist now open.
The Codex app appears to be rolling out in-app browser upgrades, including multiple viewports, screenshot viewing, improved annotations, and better token efficiency.
OpenAI’s latest post explains how it’s deploying Codex with tighter sandboxing, approval gates, and policy controls to reduce risky actions. It also highlights deep logging via OpenTelemetry so teams can audit prompts, tools, and network activity.
OpenAI has just rolled out a new Codex Chrome plugin designed to boost browser-based dev work, from testing web apps to gathering context across tabs. Early reactions are mixed, with praise for the workflow and questions about auth, profiles, and reliability.
OpenAI’s Codex CLI 0.128.0 appears to introduce a new /goal command aimed at keeping a task “alive across turns” until it’s done. Early testers say it requires a config toggle and isn’t supported in the app yet, with some reporting setup errors.