,
7 tweets,
2 min read
Read on Twitter
Historically, there have been two opposing views of cognition. One in which intelligence is a general ability to learn from arbitrary data, and one in which intelligence is the result of a myriad of special-purpose systems shaped by millions of years of evolution.
The first view derives from Enlightenment thinkers, themselves influenced by the ancients. This seems to be the position of most deep learning newbies today. The second view originates with Darwin, and was embraced by first-generation AI thinkers like Minsky, etc.
According to the first view, the mind could be seen as a "blank slate" (or a randomly initialized neural network) capable of making sense of any problem or environment, without requiring hard-wired priors.
If you take this PoV, a freshly initialized human brain placed in the body of an octopus-like creature living in the higher layers of Jupiter's atmosphere would have no issue taking control of the sensorimotor capabilities of the alien body, socialize with other octopii, etc.
..and would perhaps end up building an advanced technological civilization, and spread to the rest of universe. In this view, such a thing as "artificial general intelligence" could exist, and a human brain would be an example of it.
According to the second view, the mind is a collection of advanced cognitive processes hard-wired by evolution, and being merely tuned through embodied experience. Humans' ability for language, for ex, would be an evolved prior, something that thinkers like Chomsky have defended.
Importantly, it has been at least 15 yrs since we've gathered enough evidence to rule out both views. Although the second view has largely fallen out of favor, the first view is, shockingly, still going strong among people who have no context on the history of cognitive science.
