Arc-AGI-2 and ARC Prize 2025 • Hacker News Board

Re: Arc-AGI-2 and ARC Prize 2025

#101

Post by cubefox » Thu, Mar 27, 2025, 6:44 AM UTC

colordrops wrote: post #99

cubefox wrote: post #98

Earlier quoted context omitted.

I would argue that also small children and even most animals count as "general" intelligences. Animals are much less intelligent than grown humans, but that doesn't mean they are less general. Just like, say, AlphaGo 2 is more intelligent but not more general than AlphaGo 1. Or Qwen 32B vs Qwen 7B. Model or brain size alone doesn't determine generality. Generality is more a question of architecture.

Is there a formal or at least clear consensus definition of "general" intelligence? I assume it involves some level of autonomy and ability to manage novel situations.

There is no consensus on this.

> I assume it involves some level of autonomy and ability to manage novel situations.

Yeah. Also operating in real-time (robotics) and being able to process sensory data only, instead of relying on preprocessed data like text tokens.

Re: Arc-AGI-2 and ARC Prize 2025

#102

Post by YeGoblynQueenne » Thu, Mar 27, 2025, 9:28 PM UTC

bubblyworld wrote: post #96

YeGoblynQueenne wrote: post #94

Earlier quoted context omitted.

>> The first time a top lab spent millions trying to beat ARC was actually in 2021, and the effort failed. Which top lab was that? What did they try? >> ARC was the only benchmark that highlighted o3 as having qualitatively different abilities compared to all models that came before. Unfortunately observations support a simpler hypothesis: o3 was trained on sufficient data about ARC-1 that it could solve it well. The…

I'm sorry, but what observations support that hypothesis? There were scores of teams trying exactly that - training LLMs directly on Arc-AGI data - and by and large they achieved mediocre results. It just isn't an approach that works for this problem set. To be honest your argument sounds like an attempt to motivate a predetermined conclusion.

In which case what is the point of your comment? I mean what do you expect me to do after reading it, reach a different predetermined conclusion?

Re: Arc-AGI-2 and ARC Prize 2025

#103

Post by bubblyworld » Fri, Mar 28, 2025, 5:36 AM UTC

YeGoblynQueenne wrote: post #102

bubblyworld wrote: post #96

Earlier quoted context omitted.

I'm sorry, but what observations support that hypothesis? There were scores of teams trying exactly that - training LLMs directly on Arc-AGI data - and by and large they achieved mediocre results. It just isn't an approach that works for this problem set. To be honest your argument sounds like an attempt to motivate a predetermined conclusion.

In which case what is the point of your comment? I mean what do you expect me to do after reading it, reach a different predetermined conclusion?

Provide some evidence for your claims? This empty rhetoric stuff in every AI thread on HN wears me out a bit. I apologise for being a little aggressive in my previous comment.