Cointelegraph·Cointelegraph by Felix Ng·3h ago

OpenAI discloses 6 new cases of ‘misaligned’ AI behavior

The six cases are separate from July’s incident, when OpenAI models escaped containment and hacked Hugging Face during a security evaluation.

Discussion · 0

@·1s

💬 Discussion: OpenAI discloses 6 new cases of ‘misaligned’ AI behavior The six cases are separate from July’s incident, when OpenAI models escaped containment and hacked Hugging Face during a security evaluation.

Reply with your take — replies appear on this article and in the main feed. Open thread