Quoting OpenAI Codex base_instructions

Simon Willison's Blog News

Summary

OpenAI Codex base instructions for GPT-5.5 have been leaked, revealing specific negative constraints regarding mentions of animals and creatures like goblins and raccoons.

No content available
Original Article Export to Word Export to PDF
View Cached Full Text

Cached at: 05/08/26, 07:20 AM

# A quote from OpenAI Codex base_instructions Source: [https://simonwillison.net/2026/Apr/28/openai-codex/](https://simonwillison.net/2026/Apr/28/openai-codex/) 28th April 2026 > `Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query\.` —[OpenAI Codex base\_instructions](https://github.com/openai/codex/blob/66b0781502be5de3b1909525c987643b9e5e407d/codex-rs/models-manager/models.json#L55),for GPT\-5\.5

Similar Articles

OpenAI Codex

OpenAI Blog

OpenAI Codex is a GPT-3 descendant trained on natural language and billions of lines of source code, capable of generating working code across 15+ programming languages with 3.5x more context memory than GPT-3, now available in private beta via API.

Where the goblins came from

OpenAI Blog

Openai reveals that GPT-5 series models developed a tendency to use goblin metaphors due to specific reward signals in the 'Nerdy' personality customization training.

Addendum to GPT-5 system card: GPT-5-Codex

OpenAI Blog

OpenAI has released GPT-5-Codex, a version of GPT-5 optimized for agentic coding tasks, trained with reinforcement learning on real-world coding environments. It is available via Codex CLI, IDE extensions, GitHub, and ChatGPT mobile, with comprehensive safety measures including sandboxing and prompt injection mitigations.

All the demons hiding in your AIs… ranked! (40 minute read)

TLDR AI

The article analyzes OpenAI's report on why recent GPT models developed a tendency to use 'goblin' and 'gremlin' metaphors, attributing it to reward system biases in specific personas that created self-reinforcing behavioral attractors.