Human vs. Machine Reasoning
Andrew discusses how humans and machines exhibit biases in reasoning, drawing parallels between tokenization correlations in models and human logical inference tasks. He highlights how familiarity influences human reasoning and suggests that education can help mitigate biases in both humans and models.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#74 Dr. ANDREW LAMPINEN - Symbolic behaviour in AI [UNPLUGGED]
Related Questions