bongard

Or, ARC might go the way of the Bongard Problems [3]: the original 100 problems by Bongard still stand unsolved, but the machine learning community has effectively sidestepped them.

This also reminds me of the attempt by a researcher to develop an AI to solve bongard problems.

Is it possible that Bongard Problems are a true test of (visual) reasoning that requires intelligence to be solved?

And yet, in both Bongard problems and Winograd schemas, neural nets have now achieved high accuracy.

Not to mention the mind-blowing arrogance and ignorance he displays in believing that his research (on Bongard problems, for God's sake!

For example, the Wikipedia article on AI-completeness mentions Bongard problems and Autonomous driving as examples of problems that might be AI-complete.

Can a Bongard problem-solving AI be made, by some known procedure to drive a car?

Benchmarks like the Bongard problems, or ARC, now, are just educated guesses about the kind of behaviour an intelligent system should exhibit.

In all, our work attains state-of-the-art performance on the two main Bongard datasets.

Interestingly, Bongard problems do not have a private test set, unlike ARC-AGI.

Look up 'bongard problems' and appreciate that while some are based around topological or temporal progression, others require cataloging random arrangements and establishing membership criteria.

See the Winograd Schema Challenge (but not yet the Bongard problems).

There are much better "A-IQ tests", like the Winograd Schmea or Bongard Problems, or more recent ones like the Abstraction and Reasoning Corpus.

“We need to create technological solutions that grow at the same rate as the challenges we face,” Bongard says.

Regarding the value of "pointless pattern matching" in particular, I would refer you to Douglas Hofstadter's discussion of Bongard problems starting on page 652 of _Godel, Escher, Bach_.

Money quote: "I believe that the skill of solving Bongard [pattern recognition] problems lies very close to the core of 'pure' intelligence, if there is such a thing."

> According to Bongard, that's because these AIs are, in a sense, too heady.

Someone made a generator of Bongard-like problems [4], and while this was not enough to solve the original problems, everyone simply switched to training CNNs and reporting results on the new dataset [5].

Bongard Problems don't and they still stand undefeated (although the ANN community has sidestepped them in a sense, by generating and solving similar, but not identical, sets of problems, then claiming triumph anyway).