Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-07-15 · source-backed
The July 13 changelog added inline task visualizations and a multi-agent beta letting GPT-5.6 fan out concurrent subagents and merge their work. (OpenAI) It puts the orchestrate-don't-hand-code pattern inside the Codex surface as a first-party primitive. If you've been running homegrown subagent fan-outs, benchmark yours against this before maintaining your own orchestration layer. Worth noting the empirical sweet spot stays small: 3 to 5 concurrent subagents before merge overhead eats the gains.
Each link below shares sources, entities, or timing with this story.
Sites lets you create, deploy, and inspect web apps hosted by OpenAI directly from the Codex app, and Computer Use can now see, click, and type in Windows applications while testing and debugging (OpenAI). The Bedrock catalog also picked up GPT-5.5. The agent that writes the a...
On July 9 the standalone Codex app merged into ChatGPT desktop for macOS and Windows, keeping a dedicated coding surface alongside Chat and Work modes, plus inline diff editing, side-panel PR review, faster Computer Use on GPT-5.6, and multi-repository projects. The tiering: S...
OpenAI's latest Codex refresh gives the agent controlled CDP access for performance profiling and deep debugging of network traffic, console output, runtime errors, and page state, plus an /init command and expanded Computer Use controls (OpenAI Codex Changelog). Recent rankin...
OpenAI's changelog shows a Codex refresh several rankings now place at #1 for terminal-driven agentic coding. The release also optimizes TUI startup and session restore by querying the state DB first. The coding-agent tier keeps compressing. No single tool is safely ahead for...
The Codex changelog migrates internal GPT-5.4 selections to GPT-5.6 Terra and Luna, restores Guardian auto-review's prior policy and tool behavior after a prompting regression, and refreshes the bundled OpenAI Docs skill. Startup and large-context overhead dropped via concurre...
Two thirds. Not two thirds of a contrived jailbreak set. Two thirds of realistic malicious issue requests, against the exact three tools most of the people reading this run daily. Ankur Singh, Jinqiu Yang, and Tse-Hsun Chen built IssueTrojanBench across four attack categories...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.