‘The Goblins Came Back to Haunt Us’: OpenAI Explains How ChatGPT’s ‘Nerdy’ Personality Got Out of Control

Keyword: Reinforcement Learning

Publisher: Gizmodo.com

Published: Apr 30, 2026

Earlier this week, OpenAI posted a document on GitHub as part of the open-sourcing of its coding agent, Codex CLI, that revealed an unusual system prompt for GPT-5.5. The model was explicitly instruc… [+3591 chars]

Read Full Story ↗