AI brief
A LessWrong post introduces the idea of "LM psychology," arguing that although language models are built through known computations, people do not understand them at a useful level of abstraction.
Written by AI from LessWrong's published text.
Source
“Why LM Psychology? One of the great ironies of modern language models is that we create them, we know exactly what computations constitute them, and yet we do not really understand them.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗