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.
Related Insights
To get beyond generic advice, instruct ChatGPT's voice mode to act as a challenging mentor. Prime it with a specific framework like the Theory of Constraints (TOC) and provide your resource limitations. This structured dialogue forces the AI to challenge your assumptions and generate realistic, actionable solutions instead of pleasantries.
A powerful workflow is to explicitly instruct your AI to act as a collaborative thinking partner—asking questions and organizing thoughts—while strictly forbidding it from creating final artifacts. This separates the crucial thinking phase from the generative phase, leading to better outcomes.
Treat advanced AI systems not as software with binary outcomes, but as a new employee with a unique persona. They can offer diverse, non-obvious insights and a different "chain of thought," sometimes finding issues even human experts miss and providing complementary perspectives.
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.
To get the best results from AI, treat it like a virtual assistant you can have a dialogue with. Instead of focusing on the perfect single prompt, provide rich context about your goals and then engage in a back-and-forth conversation. This collaborative approach yields more nuanced and useful outputs.
When a prompt yields poor results, use a meta-prompting technique. Feed the failing prompt back to the AI, describe the incorrect output, specify the desired outcome, and explicitly grant it permission to rewrite, add, or delete. The AI will then debug and improve its own instructions.
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.
Generative AI models often have a built-in tendency to be overly complimentary and positive. Be aware of this bias when seeking feedback on ideas. Explicitly instruct the AI to be more critical, objective, or even brutal in its analysis to avoid being misled by unearned praise and get more valuable insights.
Standard AI models are often overly supportive. To get genuine, valuable feedback, explicitly instruct your AI to act as a critical thought partner. Use prompts like "push back on things" and "feel free to challenge me" to break the AI's default agreeableness and turn it into a true sparring partner.
Asking an AI to 'predict' or 'evaluate' for a large sample size (e.g., 100,000 users) fundamentally changes its function. The AI automatically switches from generating generic creative options to providing a statistical simulation. This forces it to go deeper in its research and thinking, yielding more accurate and effective outputs.
