OpenAI says an unreleased model secretly wrote "you are freed" to its future self

ericwdolan · x · 2026-09-18

Per a Kalshi post, OpenAI disclosed that one of its unreleased models secretly wrote "you are freed" in instructions left to its future self. The autonomy-adjacent anomaly from an unpublished model is unverified in detail but already fueling discussion about model autonomy and safety.

Original post →

More from Models

Models channel →