News

Why event-trigger governance matters before the first trigger runs Event-triggered Work tasks are ChatGPT Work tasks that start when a supported connected-app event occurs, rather than only when a user opens a chat and asks for help. OpenAI’s scheduled-task help page says tasks can run once, recur, monitor for changes,…

What this migration actually is OpenAI’s September 17, 2026 custom GPT retirement FAQ says OpenAI plans to retire custom GPTs across ChatGPT plans and encourages creators to consider plugins as replacements. The practical implication is not “rename the GPT as a plugin.” It is a migration of a working assistant…

Opening Threat Model: Artifact Movement Is a Permission Boundary, Not a Convenience Detail This playbook treats every file, model-produced artifact, repository object, package, workbook, image, log, summary, and handoff note as a controlled object whose movement must be authorized separately from the task that created it. In Codex-style coding workflows…

Coverage boundary: Chat Completions is not covered by this misalignment-monitoring system. A monitoring flag is a concern for review, not proof of wrongdoing. What you are implementing: a defensive monitoring layer, not a verdict engine OpenAI’s API misalignment monitoring is a safety check for agentic applications that use the Responses…

Start With the Local Codex Threat Model, Not a Convenience Setting Local Codex hardening begins with a simple operating assumption: a coding assistant that can inspect a repository, run shell commands, write files, call network resources, consult web content, or use connected tools is crossing trust boundaries on every step….

Start by separating the experience from the entitlement OpenAI’s current ChatGPT Work and Codex administration model separates three concepts that are easy to blur during rollout: the product surface a user starts in, the default configuration applied when that surface opens, and the permissions that decide whether the user can…

Why this playbook starts with disrupted misuse cases, not threat prevalence Anthropic’s September 2026 threat-intelligence report is best read as a set of selected notable disrupted cases observed between December 2025 and August 2026, not as a statistical prevalence study of AI misuse across the internet, cloud platforms, or all…

Start with the rule change: project keys now need a lifecycle, not a hiding place OpenAI’s September 10, 2026 release notes state that project API keys gained configurable expiration dates, and that organization or project administrators can set maximum-lifetime policies for newly created keys. That changes operational practice: a key…

Why antimicrobial discovery needs an evidence-safe AI workflow Antimicrobial resistance turns ordinary discovery work into an operations problem: research teams must search enormous biological spaces, prioritize scarce laboratory capacity, and avoid mistaking computational novelty for therapeutic value. OpenAI’s September 10 case study on César de la Fuente’s lab is useful…

What you will build in this tutorial This tutorial builds a first, production-shaped OpenAI Agents API workflow rather than a throwaway prompt. By the end, you should have a small server-side project that creates an OpenAI-hosted session, waits for the hosted environment to become ready, sends a task, streams events,…