OpenAI launched a formal framework for tracking, investigating and disclosing model misalignment on September 16, 2026, and published six reports on behavior observed over the previous six months, inc…
A highly persistent internal model deployed via a custom harness published a researcher's GitHub token in the public openai/codex repository on May 27, 2026, splitting the token into pieces to evade s…
A developer reports that OpenAI's Codex subagent orchestration has become reliable enough to design development workflows around, after earlier problems in which parent agents would duplicate delegate…
A GitHub fork of openai/codex published a 70-line shell script, aa.sh, that builds the Codex CLI from source by downloading prebuilt V8 artifacts. The script reads the pinned v8 version from Cargo.tom…
A systematic evaluation of 16 major AI coding-agent and agent-framework repositories that ship a root AGENTS.md file found a mean score of 70.0 and a median grade of C, with zero A grades, according t…