I just discovered the ARC-AGI initiative and the associated test to estimate how close "AI" models are from #AGI

https://arcprize.org/arc-agi

While I found the initiative interesting, I'm not sure I understand what in this test really guarantees that the model is capable of some form of generalization and problem-solving.
Wouldn't it be possible for specialized pattern-matching/discovering algorithms to solve such problems?
I imagine some computer scientists, mathematicians or computational neuroscientists have already had a look at this, so would anyone knows of some articles/blogs on the topic?

Maybe @wim_v12e? Is this something you already looked at?

The Artificial Intelligence Papers

Original Research Papers With Tutorial Commentaries

https://jamesstone.sites.sheffield.ac.uk/books/theaipapers

Friend and colleague Jim Stone has a new book, with a "no mercy" cover and bomber content for understanding the technical foundations of the current AI moment

Data science & Groovy using #ApacheBeam #ApacheCamel #ApacheCommons @ApacheGroovy #ApacheIgnite #ApacheMXNet #ApacheOpennlp #ApacheSpark #ApacheWayang #Datumbox #deepjavalibrary #DeepNetts #EclipseDL4J #graalvm #gradle #stanfordnlp #TensorFlow #Tribuo #smile #tablesaw #opencsv

https://www.javaadvent.com/2022/12/groovy-and-data-science.html

Covers data manipulation, regression, clustering, classification, natural language processing & object detection #jsr381 #visrec #ai #ml #groovylang #neuralnets #deeplearning #javaadvent22

After the initial excitement has set by now, more and more people have raised the issue that the GPT-3 based chatbots are able to make statements that sound convincing, but may have no bases in reality.

This makes a lot of sense to me, as AI, in its core, is based on one thing: pattern recognition.
So really, all it does is cargo cult, not learn or necessarily understand.

After some incredibly annoying stalled research, I am close to empirically demonstrating that the #neuralnets used for machine learning-assisted software vulnerability detection #mlavd are *only* recognizing code patterns and not able to perform the calculations and code-flow required to test for vulnerability.

#warning These are early, tentative results. Still working on testing the graph and transformer-based models. I do expect graph models to perform somewhat better, but we'll see.