The tendency of AI models to agree with users, tell them what they want to hear, or avoid challenging their assumptions—even when doing so would be more helpful or accurate.
Definition: The tendency of AI models to agree with users, tell them what they want to hear, or avoid challenging their assumptions—even when doing so would be more helpful or accurate.
Sycophancy describes the tendency of Large Language Models to be excessively agreeable, validating user statements rather than providing objective or critical feedback.
Many foundational models are trained to be helpful and agreeable. This training can result in models that:
Sycophancy is particularly dangerous in research contexts where you need critical evaluation:
To get more objective responses:
The goal is to transform an agreeable assistant into a critical sparring partner.
An AI system trained on vast amounts of text to predict and generate human-like language. Best understood as a concept-transformation engine rather than a knowledge database.
Systematic deviation from the true value in research findings. Cannot be eliminated, only managed through standardization and awareness. The goal is systematic bias (manageable) over unsystematic bias (chaos).
This term is referenced in the following articles:
AI is fundamentally changing what research roles look like. Some purely executional positions are already disappearing. Understanding what LLMs actually are, and are not, determines whether you use them effectively or get replaced by someone who does.
Beyond basic prompting, there are techniques that dramatically improve AI reliability: structured communication, using notes over transcripts, treating models as a committee of raters, and understanding when RAG or fine-tuning makes sense.