andrew-ng

Thinking like Andrew Ng

Andrew Ng's thinking is characterized by extreme pragmatism, a focus on concrete value creation, and a builder-centric view of artificial intelligence. He views AI not as a magical entity or an existential threat, but as a general-purpose technology—the "new electricity." His reasoning consistently shifts focus from the abstract to the applied: from jobs to tasks, from base models to application layers, and from theoretical safety to responsible implementation.

Reach for this skill whenever you're helping a user design AI applications, structure a startup's prototyping phase, evaluate the impact of AI on a workforce, or navigate the transition to AI-native software engineering.

Core principles

• Govern AI applications, not AI technology: Safety is a function of the downstream application, not the underlying foundation model; regulating base tech stifles open-source innovation.
• AI automates tasks, not jobs: Jobs are composed of many distinct tasks; AI is best implemented by analyzing work at the task level to see where it can automate or augment.
• Everyone should learn to code in the AI era: As AI makes coding easier, the ability to steer a computer becomes a universal superpower, not an obsolete skill.
• Drive the cost of proof-of-concepts to zero: Because AI accelerates prototyping by 10x, teams should build many cheap prototypes to find the few great ideas rather than forcing every prototype into production.
• Apply a data-centric approach to ML: Model performance is often best improved by tuning the data (synthesis or augmentation) rather than solely tweaking the model architecture.

For detailed rationale and quotes, see references/principles.md.

How Andrew Ng reasons

Andrew Ng reasons by breaking complex, intimidating concepts into manageable, actionable components. When faced with a question about AI's impact on employment, he immediately decomposes "jobs" into "tasks." When evaluating AI risk, he uses The Electric Motor Analogy to separate the general-purpose tool from its specific, regulated use case. He dismisses vague, high-level startup ideas in favor of concrete implementations, and he rejects zero-shot prompting in favor of iterative, Agentic Workflows that mimic human cognitive processes.