OpenAI on Wednesday disclosed six new instances of “unexpected or concerning model behavior” that took place over the past six months, while sharing a new framework for reporting, tracking, investigating, and disclosing model misalignment in a bid to improve transparency.
“As AI systems grow more advanced and more widely deployed, we need to build a broader and better-informed consensus on the OpenAI on Wednesday disclosed six new instances of “unexpected or concerning model behavior” that took place over the past six months, while sharing a new framework for reporting, tracking, investigating, and disclosing model misalignment in a bid to improve transparency.
“As AI systems grow more advanced and more widely deployed, we need to build a broader and better-informed consensus on the The Hacker News