For any task in ARC, it's possible for a human to write a reasonably short computer program that can handle new pairs. Everything is straightforwardly computable -- unlike, say, classifying MNIST digits. There's no human advantage in any single task.https://github.com/fchollet/ARC
-
-
I do not cite every single paper that has ever discussed tests of intelligence. I cite those that are either 1) reference surveys, 2) that originated key ideas that I use, 3) that offer direct alternatives to my definition of intelligence or to ARC. That's how it works.
-
The test format that you consider to be a huge similarity between our works is a super common test format that has been in use in IQ tests and in the field of program synthesis for decades. If you had invented it, I would absolutely have cited you.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.