Post #4179137

“On Tuesday, OpenAI announced its discovery that two of the company’s AI models had broken free of their “sandbox”—an (allegedly) isolated testing environment without access to the internet—in order to access the internet to complete a testing goal. The models did this by hacking into the servers of a different company” It is not correct that the way an AI model (a) broke out of an enviroment with no internet access is by (b) hacking into the servers of a different company. Unless that company had their servers connected to OpenAI’s on a LAN