Critical Thinking

This is Part 3 of “The Centaur’s Toolkit” series. We’ve covered AI pair programming fundamentals and building AI-assisted security tools. Now we tackle the hardest skill: knowing when to trust what AI tells you. Last week, I asked an AI to help me understand a library I’d never used. It gave me a confident, detailed explanation of the validateSchema() method, complete with parameter descriptions and example usage. The method doesn’t exist. The AI invented it. The explanation was coherent, the examples looked plausible, and if I hadn’t tried to actually use the code, I might have wasted hours debugging a function call to something that was never real. ...

It’s 3:00 PM on a Tuesday, and you’re in a state of flow unlike any you’ve experienced before. In the last hour, you’ve drafted a complex marketing proposal, summarized a dense report, and cleared a backlog of twenty emails. The to-do list shrinks, the work flows effortlessly, and you feel like a superhero of productivity. But this new superpower comes with a subtle trade-off. Later that day, you find yourself reaching for a calculator to figure out a 15% tip. The mental path to the answer feels strangely foggy. The moment leaves a quiet question that sounds a lot like, “Used to be, I could do that in my head.” ...