Holy moly. How did you arrive to that conclusion? Why do you think openai and anthropic train their models to generate scripts instead of tool calls now? Maybe you work there, or maybe not good enough?

Calling scripts wins long term. Maybe you haven't had a chance to work with agents for months on the same task and observing them getting looped. That is your ignorance talking.

Why am I even discussing it with people who don't understand basic costs of time and money, ffs.