Greedy, Brittle, Opaque, and Shallow: The Downsides to Deep Learning

Re:Greedy, Brittle, Opaque, and Shallow: The Downsides to De... by mikevin on Saturday February 10, 2018 @07:57PM (#16350538)

I think writing Macbeth isn't a good indicator of anything except being Shakespeare. Asking it a few questions about some general concepts like logic, math, and patterns(relationships in Macbeth maybe?) would probably yield results that are much more likely to pass the test.

[ Parent | on HN ]

Re:Greedy, Brittle, Opaque, and Shallow: The Downsides to De... by vladf on Saturday February 10, 2018 @08:32PM (#16350658)

I disagree on all counts. The first program that would be generated by such a procedure would very likely be the constant program that happens to always respond with the correct questions to your test. It depends how you randomly generate code, of course, but I doubt the complexity of a "general AI program" would ever be smaller than the complexity of the constant program which by luck returns the correct answer to your test.

[ Parent | on HN ]

Re:Greedy, Brittle, Opaque, and Shallow: The Downsides to De... by mattnewton on Saturday February 10, 2018 @09:46PM (#16350904)

Generate the Math tests then? That prevents constants.

Generating macbeth is a prompt most people here couldn’t pass, myself included...

[ Parent | on HN ]

Re:Greedy, Brittle, Opaque, and Shallow: The Downsides to De... by homarp on Saturday February 10, 2018 @09:37PM (#16350868)

you can still use generating Macbeth as a good indicator, just by providing some inputs and constraints.

Input is a Macbeth outline/play summary (e.g. https://www.cliffsnotes.com/literature/m/macbeth/play-summar... ) Contraints are "in the style of : KingLear and Othello"

and compare the produced text to Macbeth

[ Parent | on HN ]