Group items tagged

Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - also known as scheming. We study whether models have the capability to scheme in pursuit of a goal that we provide in-context and instruct the model to strongly follow. We evaluate frontier models on a suite of six agentic evaluations where models are instructed to pursue goals and are placed in environments that incentivize scheming

All primary school children in England are required to write computer programs and learn about computational thinking. There are moves in other countries to this effect such as the U.S. K-12 Computer Science Framework (CSF) for development.