Agents are opaque and we are embedding them into every digital interaction that we have
Excellent analysis, you articulate the black box issue perfectly. Given the 'trillions of parameters' and the rise of 'Agentic' software, how do you see mechanistic interpretability scaling efectively?
Excellent analysis, you articulate the black box issue perfectly. Given the 'trillions of parameters' and the rise of 'Agentic' software, how do you see mechanistic interpretability scaling efectively?