Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Untitled topic

news.ycombinator.com

Post reply on HN
Print view View original

1–10 of 61 posts

Re: undefined

#3

Post by accheng »

As an author of the blog, I'll note that this was one of the easiest applications of ADRS. Bowen, who was leading this effort, got things running within a day or two and the initial runs were with free Google credits! It was exciting to see how quickly these kinds of frameworks could be applied to real-world engineering and algorithmic challenges.

Re: undefined

#4

Post by logicallee »

accheng wrote: post #3

As an author of the blog, I'll note that this was one of the easiest applications of ADRS. Bowen, who was leading this effort, got things running within a day or two and the initial runs were with free Google credits! It was exciting to see how quickly these kinds of frameworks could be applied to real-world engineering and algorithmic challenges.

did AI explain its thinking, or could it have just stumbled upon the solution without designing it or understanding why it worked? i.e. could it have just been a hallucination that happened to work?

Re: undefined

#5

Post by accheng »

logicallee wrote: post #4
accheng wrote: post #3

As an author of the blog, I'll note that this was one of the easiest applications of ADRS. Bowen, who was leading this effort, got things running within a day or two and the initial runs were with free Google credits! It was exciting to see how quickly these kinds of frameworks could be applied to real-world engineering and algorithmic challenges.

did AI explain its thinking, or could it have just stumbled upon the solution without designing it or understanding why it worked? i.e. could it have just been a hallucination that happened to work?

This is a great question! By analyzing the logs of OpenEvolve with the full model outputs, we observed how the AI got its ideas (seemed to be pulling from literature in the space) and how it tried to apply them. So in some sense, it "reasoned" about how to get better algorithms. And we saw this process proceed systematically via the ADRS framework to converge to a significantly better algorithm

Re: undefined

#6

Post by _--__--__ »

Nice result, but the snake pattern is pretty obvious and intuitive even for a human who just glances over the problem. It kinda breaks if there is huge variance (if the top load expert is orders of magnitude higher than #2 it probably should just get its own GPU), but I'm not familiar enough with MoE to know if that's a realistic possibility.

Re: undefined

#8

Post by abmfy »

_--__--__ wrote: post #6

Nice result, but the snake pattern is pretty obvious and intuitive even for a human who just glances over the problem. It kinda breaks if there is huge variance (if the top load expert is orders of magnitude higher than #2 it probably should just get its own GPU), but I'm not familiar enough with MoE to know if that's a realistic possibility.

Thanks! In realistic workloads, the differences won’t be orders of magnitude.

I agree that this is a fairly simple problem. Experienced engineers—or anyone who has faced similar challenges—can quickly come up with such solutions. The key point, however, is that others might get stuck in their research simply because they don’t realize these quick solutions exist (“I don’t know what I don’t know”). AI helps bridge that gap by making expert-level knowledge accessible to every researcher, allowing them to focus more on exploring the truly unknown parts.

Re: undefined

#9

Post by logicallee »

accheng wrote: post #5
logicallee wrote: post #4

Earlier quoted context omitted.

did AI explain its thinking, or could it have just stumbled upon the solution without designing it or understanding why it worked? i.e. could it have just been a hallucination that happened to work?

This is a great question! By analyzing the logs of OpenEvolve with the full model outputs, we observed how the AI got its ideas (seemed to be pulling from literature in the space) and how it tried to apply them. So in some sense, it "reasoned" about how to get better algorithms. And we saw this process proceed systematically via the ADRS framework to converge to a significantly better algorithm

very interesting, thank you.
Post reply on HN