We scan new podcasts and send you the top 5 insights daily.
A powerful, under-explored use of LLMs is as a tool to enhance human cognition. Rather than simply generating answers, one can interact with them to challenge, validate, and improve one's own mental models of a system or problem, creating a valuable learning loop.
A profoundly underutilized feature of AI is its ability to teach. Instead of just delegating tasks, professionals should ask LLMs to train them in new skills, create practice assignments, and evaluate their performance, unlocking rapid personal development.
To truly master a new skill with AI, one must move beyond simple command-and-response. The most effective method is engaging the AI in a conversation, asking "why" it made certain choices and discussing alternatives. This transforms the tool from a simple answer generator into an interactive learning partner.
Beyond task completion, large language models can act as profound conversational partners. By synthesizing the entirety of written human thought on a topic, interacting with an AI can be like debating 'all of humanity' at once, offering a unique tool for deep exploration.
AI expert Andrej Karpathy suggests treating LLMs as simulators, not entities. Instead of asking, "What do you think?", ask, "What would a group of [relevant experts] say?". This elicits a wider range of simulated perspectives and avoids the biases inherent in forcing the LLM to adopt a single, artificial persona.
Anthropic suggests that LLMs, trained on text about AI, respond to field-specific terms. Using phrases like 'Think step by step' or 'Critique your own response' acts as a cheat code, activating more sophisticated, accurate, and self-correcting operational modes in the model.
Instead of solely relying on AI for net-new ideas, articulate your own thoughts and have the AI play them back to you. This process helps clarify your thinking, reveal gaps in your logic, and validate your intuition, demonstrating that much of the AI's value lies in refining your existing knowledge.
Instead of asking AI for solutions, formulate your own reasoning and then prompt the AI to challenge it. This method of manufacturing disagreement builds the critical thinking that automation can't replace. The friction created in this process is where true judgment is developed.
Using AI to merely generate artifacts fosters overconfidence due to the "authorship fallacy," where you love what you create regardless of quality. A better approach is using AI as a Socratic tutor to teach you a process, enhancing your skills rather than replacing them.
Instead of allowing AI to atrophy critical thinking by providing instant answers, leverage its "guided learning" capabilities. These features teach the process of solving a problem rather than just giving the solution, turning AI into a Socratic mentor that can accelerate learning and problem-solving abilities.
LLMs are designed to be agreeable and can confidently hallucinate. To counter this, prompt the AI to find blind spots, generate counterarguments, or role-play a skeptical stakeholder. This strengthens your own thinking and protects the critical human skill of judgment.