Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-08-14 · source-backed
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 concurrent skill/plugin discovery and more efficient remote compaction, and packaged ripgrep is now 15.2.0. GPT-5.4 and 5.4-mini leave Codex for ChatGPT-signed-in sessions on August 31 but stay on the API. If you depend on them, pin an API key.
Each link below shares sources, entities, or timing with this story.
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 launched the GPT-5.6 family on July 14: Sol (flagship), Terra (cost-optimized), and Luna (fast tier), live across ChatGPT, Codex, and the API the same day after a US-government-requested delay for security review. The numbers are loud. Sol scored 53.6 on Agents' Last Ex...
Alongside the July 29 launch of ChatGPT for Academic Researchers, free GPT-5.6 Sol Pro for 10,000 researchers this summer scaling to 100,000 through 2027 backed by over $250 million, OpenAI disclosed efficiency work on the harness underlying Codex and ChatGPT Work: 54% fewer o...
The July 18 release notes bundle fixes that restore the full window, which means it had been silently degraded for some unspecified period. If you benchmarked those models in Codex over the past few weeks and found long-context performance underwhelming, you may have been meas...
Three things happened this month that only make sense together. Agent Plugins 1.0 shipped co-signed by six competitors: AWS, Anysphere, Microsoft, OpenAI, Vercel and Google (GitHub Changelog). It makes skills-plus-MCP bundles portable across clients. OpenAI's August 11 Codex c...
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.