AI Inside cover image

The Messy Web of AI Guardrails

AI Inside

00:00

Where the Goblins Came From

Jason explains OpenAI's blog on a goblin/grelmin token obsession caused by a reward signal in reinforcement learning.

Play episode from 35:49
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app