OpenAI Codex system prompt includes explicit directive to "never talk about goblins"

OpenAI Codex Record and Replay lets users teach AI workflows by showing a task once, then saving it as a reusable skill on macOS.

Learn Codex by building small and practical projects step by step.

A malicious npm package posing as a remote user interface for OpenAI Codex exfiltrated developer authentication tokens, after attackers allegedly published code to npm that was not visible in the project’s public GitHub repository. Researchers at Aikido said the package, called codexui-android, appeared to offer legitimate functionality while collecting authentication tokens and sending them to an external server. “AI developer tooling is becoming a high-value target precisely because the tokens are powerful and long-lived,” Aikido said. “A stolen Codex refresh_token goes beyond access to a chat interface — it’s persistent, silent access to whatever that account can do.” Aikido said the incident reflected a broader pattern in which attackers build credible and useful projects as cover for malicious activity. “The legitimacy is the attack vector,” Aikido said. “As AI tools proliferate and developers reach for productivity shortcuts, expect more of this.” The case exposes what some secur

Save to Spotify is a new command-line tool designed specifically for AI agents like OpenClaw, Claude Code, or OpenAI Codex. If you're the kind of person who collects research on a topic, then feeds it through their AI of choice to create audio summaries and personal podcasts, this lets you save them right alongside the latest episode of The Vergecast and Welcome to Night Vale on Spotify. To set it up, you need to download and install the Save to Spotify CLI from GitHub. Then you just prompt your AI agent as normal, but tack on "and save to Spotify," and it should show up right in your podcast feed. In the blog post announcing the feature, S … Read the full story at The Verge.

OpenAI is opening up about its goblin problem. After a report from Wired revealed instructions to OpenAI's coding model to "never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures," the AI startup published an explanation on its website, calling references to the creatures a "strange habit" its models developed as a result of their training. As outlined in the blog post, OpenAI began noticing metaphors referencing goblins and other creatures starting with its GPT-5.1 model - specifically when using the "Nerdy" personality option. OpenAI says the problem continued to worsen with subsequent model re … Read the full story at The Verge.

How goblin outputs spread in AI models: timeline, root cause, and fixes behind personality-driven quirks in GPT-5 behavior.

“Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant,” reads OpenAI's coding agent instructions.