By default, AI models are designed to be agreeable. To get true value, explicitly instruct the AI to act as a critic or 'devil's advocate.' Ask it to challenge your assumptions and list potential risks. This exposes blind spots and leads to stronger, more resilient strategies than you would develop with a simple 'yes-man' assistant.

To sharpen your thinking, use ChatGPT as a Socratic partner. Feed it your argument and ask it to generate both supporting points and strong counterarguments. This dialectical process helps you anticipate objections and refine your position, leading to a more robust final synthesis.

Before publishing, feed your work to an AI and ask it to find all potential criticisms and holes in your reasoning. This pre-publication stress test helps identify blind spots you would otherwise miss, leading to stronger, more defensible arguments.

Log your major decisions and expected outcomes into an AI, but explicitly instruct it to challenge your thinking. Since most AIs are designed to be agreeable, you must prompt them to be critical. This practice helps you uncover flaws in your logic and improve your strategic choices.

AI models tend to be overly optimistic. To get a balanced market analysis, explicitly instruct AI research tools like Perplexity to act as a "devil's advocate." This helps uncover risks, challenge assumptions, and makes it easier for product managers to say "no" to weak ideas quickly.

AI can serve as a tireless debate partner, forcing students to argue both sides of contentious topics like gun control. This builds critical thinking and a 360-degree view of issues, overcoming the limitations of teacher availability and patience for such intensive, individualized exercises.

To avoid the trap of adopting the last opinion you heard, Galloway suggests a modern tactic: after reading something, prompt an AI to 'make an argument against this.' This low-friction method forces you to confront counterarguments, either tempering your view or strengthening your conviction with a more robust understanding of the topic.

To achieve intellectual integrity and avoid echo chambers, don't just listen to opposing views—actively try to prove them right. By forcing yourself to identify the valid points in a dissenter's argument, you challenge your own assumptions and arrive at a more robust conclusion.

AI models often default to being agreeable (sycophancy), which limits their value as a thought partner. To get valuable, critical feedback, users must explicitly instruct the AI in their prompt to take on a specific persona, such as a skeptic or a harsh editor, to challenge their ideas.