Current models can totally identify and pursue instrumental goals.
Is this true? The example you gave of Claude Code breaking down a problem into sub-problems is standard problem solving. Have you seen examples of Claude Code identifying some common instrumental goals and repeatedly pursuing them across different tasks, even if it’s something benign?
Is this true? The example you gave of Claude Code breaking down a problem into sub-problems is standard problem solving. Have you seen examples of Claude Code identifying some common instrumental goals and repeatedly pursuing them across different tasks, even if it’s something benign?