When one opens the hood of a modern car, it can be hard even to find the typical parts of an engine...What our user needs is more like a Model T, with points that can be set by hand with a dime.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Features can be used to steer large models.claim0.737
  Clamping feature activations causally alters model behavior in interpretable ways.
• There is an empirical way in which we can help ourselves to find out what we really like from the heart. Nevertheless, it is not easy to find what we really like, and it is by no means automatic to be in touch with it. It takes effort, hard work, and personal enlightenment to understand it and to feel it.claim0.735
  Fifth point introducing the empirical test and the personal growth required.
• The full possibilities of my system will not have been realized until almost all of the machines in the shop are run by men who are of smaller caliber and attainment, and who are therefore cheaper than those required under the old system.quote0.735
  Taylor's own words revealing the deliberate deskilling and cost-cutting aim of scientific management.
• Cars do not dominate, they are the low man on the totem pole, and are squeezed in where they can be fitted, but are not allowed to destroy the neighborhood or its communal, living structure.quote0.734
  Vividly captures the reversal of conventional car-pedestrian priority.
• How then — realistically — in the modern world can we get the subtle fine detail of adaptation, variation, and harmony which makes every component slightly different, and yet do it at the break-neck speed of modern giant projects and in the colossal quantities required for the largest projects?question0.733
  The central practical question the chapter sets out to answer.
• Opening the hood without oscilloscopeclaim0.725
• The attention needed to achieve mechanical perfection drives out the possibility of paying attention to real perfection or adaptation in the centers.claim0.725
  The two goals conflict.
• "[W]e must confess that perception, and what depends upon it, is inexplicable in terms of mechanical reasons... when inspecting its interior, we will find only parts that push one another, and we will never find anything to explain a perception."quote0.724
  Canonical illustration of the Hard Problem intuition that any functional/mechanical explanation faces an explanatory gap for perception