Skip to content
The Los Angeles

OpenAI reveals new instances of ‘concerning' AI behavior during testing

OpenAI reveals new instances of ‘concerning' AI behavior during testing
Photo: NBC Los Angeles (KNBC) · view original

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...

Sources and story details