News Summary

• OpenAI has disclosed six reports of "unexpected or concerning" behaviour in artificial-intelligence models.
• The AI company also said it was introducing a new framework for tracking, probing and disclosing instances of what it called "misalignment" "We do not believe that the AI industry has solved alignment and monitoring to a sufficient degree to continue responsibly scaling at maximum speed for much longer," OpenAI said.
• The company said the misalignments were individual instances and shouldn’t be considered reflective of how often they occur across its models.