Develop AI systems to efficiently learn new skills and solve open-ended problems, rather than depend exclusively on AI systems trained with extensive datasets
Calling all developers, philosophers, and creatives!
Let share a little background about what we're working on over here at #kaggle-arc-agi. If you're interested in working on it with us, DM me and I'll help you get up to speed!
This team is where we're collaborating on a really hard problem called the Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) benchmark. This challenge measures an AI system's ability to efficiently learn new skills. Humans easily score 85% in ARC, whereas the best AI systems only score 34%.
That's still a huge gap and there's a lot a reasons why AI struggles with this. Our job is to develop an algorithm that can overcome some of these struggles. Perhaps through this challenge we will learn more about the mystery of our brains and human consciousness.
See the intro post for links to the challenge and more background on what it actually is.
This team is for collaboration around the ARC 2024 on Kaggle. Here's some background from the Kaggle page.
Discover assets like this one.