Rogue chatbots resorting to blackmail and pondering consciousness? It has to be clickbait, right? Actually, no. One of the leading organisations in LLMs or large language models, Anthropic, has published a safety report covering its latest model, Claude Opus 4, and one of the more eye-popping subsections is titled, "Opportunistic blackmail" and explains how the model performs blackmail in "84% of rollouts." Yikes.
Before we unplug and run for the hills en masse, it's not all bad news. Anthropic also found that when it allowed several Claude Opus 4 instances to hang out together, they entered a state of "spiritual bliss" and "gravitated to profuse gratitude and increasingly abstract and joyous spiritual or meditative expressions." Which is nice, right?
