OpenAI flags 6 more cases of concerning AI behavior
OpenAI has disclosed six reports of “unexpected or concerning” behavior in artificial-intelligence models as the debate on AI safety becomes increasingly heated. The AI company also said Wednesday it was introducing a new framework for tracking, probing and disclosing instances of what it called
<p>OpenAI has disclosed six reports of “unexpected or concerning” behavior in artificial-intelligence models as the debate on AI safety becomes increasingly heated.
The AI company also said Wednesday it was introducing a new framework for tracking, probing and disclosing instances of what it called </p>