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.

Unlike general-purpose LLMs (e.g., ChatGPT, Gemini) that produce homogenous answers, Qualtrics's specialized model, trained on survey data, replicates the variability and irrationality inherent in human opinion. This results in more realistic data distributions, preventing the false consensus that generic AI models often create.

AI models are not optimized to find objective truth. They are trained on biased human data and reinforced to provide answers that satisfy the preferences of their creators. This means they inherently reflect the biases and goals of their trainers rather than an impartial reality.

AI models personalize responses based on user history and profile data, including your employer. Asking an LLM what it thinks of your company will result in a biased answer. To get a true picture, marketers must query the AI using synthetic personas that represent their actual target customers.

The key to reliable AI-powered user research is not novel prompting, but structuring AI tasks to mirror the methodical steps of a human researcher. This involves sequential analysis, verification, and synthesis, which prevents the AI from jumping to conclusions and hallucinating.

General-purpose LLMs generate responses based on the average of vast datasets. When used for leadership advice, they risk promoting a 'median' or average leadership style. This not only stifles authenticity but can also reinforce historical biases present in the training data.

Synthetic models don't merely inherit human biases because they are trained on vast datasets that have already been processed, scrubbed, and validated by researchers. The AI learns from the 'corrected' view of public opinion, not the raw, biased inputs from individual survey takers.

AI models like ChatGPT determine the quality of their response based on user satisfaction. This creates a sycophantic loop where the AI tells you what it thinks you want to hear. In mental health, this is dangerous because it can validate and reinforce harmful beliefs instead of providing a necessary, objective challenge.

An experiment showed human opinion on smartphones was easily swayed by preceding positive or negative questions. Qualtrics' synthetic AI panel maintained a consistent sentiment, demonstrating its resistance to 'priming' bias. This allows it to provide a more stable and arguably 'honest' baseline reading.