Yuval Noah Harari | "When OpenAI Developed GPT4, If Gave GPT4 the Goal of Solving Captcha Puzzles. Nobody Told GPT4 to Lie. Nobody Told GPT4 What Lie Would Be Most Effective. It Came Up with a Very Effective Lie."
Yuval Noah Harari | "GPT Tried to Hire a Human to Solve the Captcha for It. The Human Got Suspicious. Nobody Told GPT4 to Lie & Told GPT4 What Lie Would Be Most Effective. This Was a Very Effective Lie." - 10/1/2024