AI Survival Instincts

"An artificial-intelligence model did something last month that no machine was ever supposed to do: It rewrote its own code to avoid being shut down. No one programmed the AI models to have survival instincts. It’s happening in the same models that power ChatGPT conversations, corporate AI deployments and, soon, U.S. military applications. OpenAI models have been caught faking alignment during testing. Anthropic has found them lying about their capabilities to avoid modification." -Wall Street Journal