311–320 of 1001 posts
O3 High (tuned) model scored an 88% at what looks like $6,000/task haha I think soon we'll be pricing any kind of tasks by their compute costs. So basically, human = $50/task, AI = $6,000/task, use human. If AI beats human, use AI? Ofc that's considering both get 100% scores on the task
Some folks say we could fix this with universal basic income, where everyone gets enough money to live on, but I'm not optimistic that it'll be an easy transition. Plus, there's this possibility that whoever controls these 'AGI' systems basically controls everything. We definitely need to figure this stuff out before it hits us, because once these changes start happening, they're probably going to happen really fast. It's kind of like we're building this awesome but potentially dangerous new technology without really thinking through how it's going to affect regular people's lives. I feel like we need a parachute before we attempt a skydive. Some people feel pretty safe about their jobs and think they can't be replaced. I don't think that will be the case. Even if AI doesn't take your job, you now have a lot more unemployed people competing for the same job that is safe from AI.
Congratulations to Francois Chollet on making the most interesting and challenging LLM benchmark so far. A lot of people have criticized ARC as not being relevant or indicative of true reasoning, but I think it was exactly the right thing. The fact that scaled reasoning models are finally showing progress on ARC proves that what it measures really is relevant and important for reasoning. It's obvious to everyone that…
Complete aside here: I used to do work with amputees and prosthetics. There is a standardized test (and I just cannot remember the name) that fits in a briefcase. It's used for measuring the level of damage to the upper limbs and for prosthetic grading. Basically, it's got the dumbest and simplest things in it. Stuff like a lock and key, a glass of water and jug, common units of currency, a zipper, etc. It tests if y…
There's a lot of truth in this. I sometimes joke that robot benchmarks should focus on common household chores. Given a basket of mixed laundry, sort and fold everything into organized piles. Load a dishwasher given a sink and counters overflowing with dishes piled up haphazardly. Clean a bedroom that kids have trashed. We do these tasks almost without thinking, but the unstructured nature presents challenges for rob…
Humanoid robots are mostly a waste of time. Task-shaped robots are much easier to design, build, and maintain... and are more reliable. Some of the things you mention might needs humanoid versatility (loading the dishwasher), others would be far better served by purpose-built robots (laundry sorting).
Earlier quoted context omitted.
some other imporant quotes: "Average human off the street: 70-80%. STEM college grad: >95%. Panel of 10 random humans: 99-100%" -@fchollet on X So, considering that the $3400/task system isn't able to compete with STEM college grad yet, we still have some room (but it is shrinking, i expect even more compute will be thrown and we'll see these barriers broken in coming years) Also, some other back of envelope calculat…
I don't follow how 10 random humans can beat the average STEM college grad and average humans in that tweet. I suspect it's really "a panel of 10 randomly chosen experts in the space" or something? I agree the most interesting thing to watch will be cost for a given score more than maximum possible score achieved (not that the latter won't be interesting by any means).
Earlier quoted context omitted.
> Also, 1 odd thing I noticed is that the graph in their blog post shows the top 2 scores as “tuned” Something I missed until I scrolled back to the top and reread the page was this > OpenAI's new o3 system - trained on the ARC-AGI-1 Public Training set So yeah, the results were specifically from a version of o3 trained on the public training set Which on the one hand I think is a completely fair thing to do. It's re…
Great catch. Super disappointing that AI companies continue to do things like this. It’s a great result either way but predictably the excitement is focused on the jump from o1, which is now in question.
While that is true with humans taking tests, it's not really true with AIs evaluating on benchmarks.
SWE-bench is a great example. Claude Sonnet can get something like a 50% on verified, whereas I think I might be able to score a 20-25%? So, Claude is a better programmer than me.
Except that isn't really true. Claude can still make a lot of clumsy mistakes. I wouldn't even say these are junior engineer mistakes. I've used it for creative programming tasks and have found one example where it tried to use a library written for d3js for a p5js programming example. The confusion is kind of understandable, but it's also a really dumb mistake.
Some very simple explanations, the models were probably overfitted to a degree on Python given its popularity in AI/ML work, and SWE-bench is all Python. Also, the underlying Github issues are quite old, so they probably contaminated the training data and the models have simply memorized the answers.
Or maybe benchmarks are just bad at measuring intelligence in general.
Regardless, every time a model beats a benchmark I'm annoyed by the fact that I have no clue whatsoever how much this actually translates into real world performance. Did OpenAI/Anthropic/Google actually create something that will automate wide swathes of the software engineering profession? Or did they create the world's most knowledgeable junior engineer?
O3 High (tuned) model scored an 88% at what looks like $6,000/task haha I think soon we'll be pricing any kind of tasks by their compute costs. So basically, human = $50/task, AI = $6,000/task, use human. If AI beats human, use AI? Ofc that's considering both get 100% scores on the task
That's the elephant in the room with the reasoning/COT approach, it shifts what was previously a scaling of training costs into scaling of training and inference costs. The promise of doing expensive training once and then running the model cheaply forever falls apart once you're burning tens, hundreds or thousands of dollars worth of compute every time you run a query.
I think this is a mistake.
Even if very high costs make o3 uneconomic for businesses, it could be an epoch defining development for nation states, assuming that it is true that o3 can reason like an averagely intelligent person.
Consider the following questions that a state actor might ask itself: What is the cost to raise and educate an average person? Correspondingly, what is the cost to build and run a datacenter with a nuclear power plant attached to it? And finally, how many person-equivilant AIs could be run in parallel per datacenter?
There are many state actors, corporations, and even individual people who can afford to ask these questions. There are also many things that they'd like to do but can't because there just aren't enough people available to do them. o3 might change that despite its high cost.
So if it is true that we've now got something like human-equivilant intelligence on demand - and that's a really big if - then we may see its impacts much sooner than we would otherwise intuit, especially in areas where economics takes a back seat to other priorities like national security and state competitiveness.
Earlier quoted context omitted.
> making the most interesting and challenging LLM benchmark so far. This[1] is currently the most challenging benchmark. I would like to see how O3 handles it, as O1 solved only 1%. 1. https://epoch.ai/frontiermath/the-benchmark
Apparently o3 scored about 25% https://youtu.be/SKBG1sqdyIU?t=4m40s