Cognitive Biases in Large Language Models

📖 Description

> Humans, one might say, are the cyanobacteria of AI: we constantly emit large amounts of structured data, which implicitly rely on logic, causality, object permanence, history--all of that good stuff. All of that is implicit and encoded into our writings and videos and 'data exhaust'. A model learning to predict must learn to understand all of that to get the best performance; as it predicts the easy things which are mere statistical pattern-matching, what's left are the hard things. [Gwern](https://www.gwern.net/Scaling-hypothesis#:~:text=Humans%2C%20one,hard%20things.) > >

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/fFF3G4W8FbXigS4gr/cognitive-biases-in-large-language-models