jargon - small but heavy
the negative connotation of jargon does not hold for ai. the way these models work, jargon likely yields the best results possible.
benefits of jargon seem to build upon themselves considering the probabilistic nature of models.
first: the raw tokens of jargon will guide the model into the desired nooks and crannies.
second: jargon is rare and jam-packed with meaning. therefore, it has a small yet heavy footprint in the context window. in other words, jargon is not only cost efficient, it also effectively extends the context window.