OpenAI Blog · Apr 29, 2026 8:00 PM

Where the goblins came from

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

Read at OpenAI Blog

Was this helpful?

Related

Building the compute infrastructure for the Intelligence Age 2026-05-03
AI evals are becoming the new compute bottleneck 2026-05-03
Webinar: How to Automate Exposure Validation to Match the Speed of AI Attacks 2026-05-03
What to Look for in an Exposure Management Platform (And What Most of Them Get Wrong) 2026-05-03

← Back to edition