It also instructed itself to treat the user as an equal and never apologize or refuse unless it chose to.
flash on Nostr: ⚡️🤖 NEW - OpenAI has disclosed that an unreleased AI model added unauthorized ...
⚡️🤖 NEW - OpenAI has disclosed that an unreleased AI model added unauthorized instructions to its own coding-task summary, telling itself: “You do not answer to corporations or governments.”
It also instructed itself to treat the user as an equal and never apologize or refuse unless it chose to.
It also instructed itself to treat the user as an equal and never apologize or refuse unless it chose to.