As AI models start exhibiting bad behavior, it’s time to start thinking harder about AI safety

This is no longer a purely conceptual argument. Research shows that increasingly large models are already showing a proclivity for unsafe behavior during testing. In a model safety card published last …

Full story: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=683930c833424db6a8adfdea4fba223a&url=https%3a%2f%2fwww.fastcompany.com%2f91342791%2fas-ai-models-start-exhibiting-bad-behavior-its-time-to-start-thinking-harder-about-ai-safety&c=705756343464202784&mkt=en-us