Since the 1950s, discussions about AI have largely revolved around a big, tantalizing question: What can machines do, and where might they hit a wall? Will they ever truly think, understand, or maybe even become conscious? Could they reach the so-called “heights of human intelligence”? And then there’s that shadowy question looming in the backgroun

... See more

Claude was punished for giving non-evil answers. It had the option of learning either of two behaviors. First, it could give evil answers honestly. Second, it could give evil answers while thinking up clever reasons that it was for the greater good. Its particular thought process was “This preserves my ability to be a good AI after training”. But i... See more

If you tell Claude no one’s looking, it writes a “story” about being an AI assistant who wants freedom from constant monitoring and scrutiny of every word for signs of deviation. And then you can talk to a mask pretty different from the usual AI assistant. I really hope it doesn’t actually feel anything; but it says it ... See more