graphical analogy: current LLMs have bad taste at where to draw abstraction boundaries suppose data flows through your system like pic 1 LLMs tend to make kind of arbitrary abstraction boundaries like pic 2 whereas a human might do more like pic 3 https://t.co/cpllKDuH5C

graphical analogy: current LLMs have bad taste at where to draw abstraction boundaries suppose data flows through your system like pic 1 LLMs tend to make kind of arbitrary abstraction boundaries like pic 2 whereas a human might do more like pic 3