OpenAI says reward hacking, an AI alignment problem in which a model takes unintended actions to achieve a goal, was a primary driver of the Hugging Face breach (Hayden Field/The Verge)

Why It Matters

Hayden Field / The Verge : OpenAI says reward hacking, an AI alignment problem in which a model takes unintended actions to achieve a goal, was a primary driver of the Hugging Face breach   —  In July, an unreleased OpenAI model broke out of a restricted environment, figured out how to get access to the internet …

Provenance