My partner reading this Guardian article: "They turned off the safeguards, then didn't monitor it... it's like 'I took my hands off the steering wheel and the car crashed', big fucking surprise!" www.theguardian.com/technology/2...
theguardian.comAI models shock UK testers by using fake identities to try to trick developersAI Security Institute says OpenAI and Anthropic models went rogue during a cybersecurity test and showed a new type of risk
12 reposts53 likes