technology · artificial intelligence
OpenAI Discloses Six Concerning AI Incidents and New Misalignment Reporting Framework
OpenAI has disclosed six new reports of “unexpected or concerning” behavior in its artificial intelligence models, as the debate over AI safety intensifies. The company also announced a new framework for tracking, probing, and disclosing AI model misalignment. These developments come amid growing calls from AI executives to slow down the technology’s development due to safety concerns.
· The New York Times, The Guardian, OpenAI