#llm #ai #mental-model #cognitive-bias
Created at 010423
# [Anonymous feedback](https://www.admonymous.co/louis030195)
# [[Epistemic status]]
#shower-thought
Last modified date: 010423
Commit: 0
# Related
- [[Computing/Intelligence/LLMs are a lever rather than an engine]]
- [[Computing/Intelligence/Evaluating LLM]]
- [[Computing/Software 3.0 llm leverage]]
- [[Computing/Making aligned LLMs end-to-end]]
- [[Computing/Prediction is compression]]
- [[Computing/NIPS 2022]]
# TODO
> [!TODO] TODO
# Battling the confirmation bias with LLMs
Say you ask a question to a [[Large language model|LLM]], then you can explicitly ask a contrarian point of view, and finally ask the LLM to play devil's advocate