Why the Abstraction and Reasoning Corpus is interesting and important for AI

Re:Why the Abstraction and Reasoning Corpus is interesting a... by meltyness on Wednesday March 01, 2023 @10:52PM (#34991777)

Right but the author's premise is that the AI fails to reason or extend ideas, not that the AI fails to reason or extend ideas in the presence of extraneous, conflicting, or malformed instructions.

If you're prompting ChatGPT (which is already loaded with prompt-engineering cheez-whiz mind you) to reason as a computer, why use words like "imagine"? why phrase things as a question? I think the fragility the author is observing here is extraneous to the actual underlying technology, and a factor of the UI that's been stacked-on and purpose-built for softer-purpose use, not hard academic research such as this.

Case study, even GPT2 can reason about the stack https://transformer.huggingface.co/share/bQXbmeyBZD

[ Parent | on HN ]

Re:Why the Abstraction and Reasoning Corpus is interesting a... by civilized on Wednesday March 01, 2023 @11:12PM (#34991904)

I don't see any extraneous, conflicting, or malformed instructions.

"Can reason" is a generous interpretation of "got the right answer in one instance".

[ Parent | on HN ]

Re:Why the Abstraction and Reasoning Corpus is interesting a... by meltyness on Wednesday March 01, 2023 @11:24PM (#34991996)

I mean unless you've got a better heuristic, but my conclusion is primarily structural with regard to Transformer units, basically that they're Turing-complete -- if there's anything more to reasoning and abstraction, I don't know myself, perhaps Scott Aaronson is the guy to talk to.

[ Parent | on HN ]