François CholletVerified account

those who are interested in this might want to check out our work on ‘cognitive programs’ where abstract concepts are learned as programs on a ‘visual cognitive computer’. And yeah, it transfers between tasks. https://www.vicarious.com/2019/01/18/a-thought-is-a-program/ …

Nice! This is remarkably similar task to ARC (table vs grid) and a powerful solution. What would it take to adapt VCC for ARC? @fchollet has an open challenge: solving ARC would get us very close to general intelligence, and it could take 2+ years.

Thanks! 'Remarkably similar' is not surprising because @fchollet read our paper before proposing ARC, but then got afflicted with source amnesia. ARC is ok, but brushes fundamental problems like 'objectness' under the carpet. Those cannot be solved using 'connect lines' etc.

You keep accusing me of plagiarism. FYI, ARC was near-finalized before your paper was released. I started working on it in late 2017. I took exactly nothing from your paper, which I vaguely skimmed after you sent it to me (which you did after I had talked to you about ARC...)

And it never occurred to me to cite your paper because it isn't a relevant citation. It doesn't constitute a reference survey, it did not originate any key idea that my paper uses, and it does not offer a direct alternative to any of the 2 things my paper proposes (ARC + def).

You don't just cite things because they share one or two vague similarities (which would involve citing tens of thousands of paper in every paper). You cite things either for attribution, or because they would constitute a useful reference for the reader to check out.