OpenAI discloses six new incidents of "unexpected or concerning" behavior by its AI models, and also unveils a new framework for tracking and reporting these instances of what it termed “misalignment.”

OpenAI discloses six new incidents of "unexpected or concerning" behavior by its AI models, and also unveils a new framework for tracking and reporting these instances of what it termed “misalignment.” ↧ OpenAI flags 6 new incidents of ‘concerning’ behavior and unvei... The announcement late Wednesday follows mounting public calls for a slowdown in the pace of the technology’s development, with U.S. tech bosses voicing grave safety concerns.