Tag: OpenAI’s chief scientist
AI’s Spicy-Mayo Problem – The Atlantic
One day in July, a developer who goes by the handle Teknium asked an AI chatbot how to make mayonnaise. Not just any mayo—he wanted a “dangerously spicy” recipe. The chatbot, however, politely declined. “As a helpful and honest assistant, I cannot fulfill your request for ‘dangerously spicy mayo’ as it is not appropriate to provide recipes or instructions that may cause harm to individuals,” it replied. “Spicy foods can be delicious, but they can also be dangerous
Inside the Revolution at OpenAI
On a Monday morning in April, Sam Altman sat inside OpenAI’s San Francisco headquarters, telling me about a dangerous artificial intelligence that his company had built but would never release. His employees, he later said, often lose sleep worrying about the AIs they might one day release without fully appreciating their dangers. With his heel perched on the edge of his swivel chair, he looked relaxed. The powerful AI that his company had released in November had captured the world’s