But that’s kind of always the issue with AI… The datasets being contaminated with the data from validation, or the benchmarks… I don’t see a fundamental change here? It’s going to be a good benchmark at first, and once the dataset is contaminated, we need a new one… As it has been the case with the previous ones… Or an I missing something here? I mean I don’t want to be overly negative… But up until autumn, you could just ask it to count the number of 'r’s in ‘strawberry’ an it’d achieve a success rate of 10%. If this is something substantial, this isn’t it.
I still don’t get it. And under “Future Model Performance” they say benchmarks quickly get saturated. And maybe it’s going to be the same for this one and models could achieve 50% by the end of this year… Which doesn’t really sound like the “last examn” to me. But maybe it’s more the approach of coming up with good science questions. And not the exact dataset??
I think the easiest way to explain this, is to say they are testing the ability to reason your way to an answer, to a question so unique, that it doesn’t exist anywhere on the internet.
The relevance of this test is that it is that the answers don’t already exist on the internet.
With previous tests, where AI scored 90%, how do we know it figured out the right answer, or just copied someone else’s from its training data?
This test better measures true independent reasoning.
But that’s kind of always the issue with AI… The datasets being contaminated with the data from validation, or the benchmarks… I don’t see a fundamental change here? It’s going to be a good benchmark at first, and once the dataset is contaminated, we need a new one… As it has been the case with the previous ones… Or an I missing something here? I mean I don’t want to be overly negative… But up until autumn, you could just ask it to count the number of 'r’s in ‘strawberry’ an it’d achieve a success rate of 10%. If this is something substantial, this isn’t it.
The dataset consists of 3,000 challenging questions across over a hundred subjects. We publicly release these questions, while maintaining a private test set of held out questions to assess model overfitting.
They say they’ve addressed this issue.
I still don’t get it. And under “Future Model Performance” they say benchmarks quickly get saturated. And maybe it’s going to be the same for this one and models could achieve 50% by the end of this year… Which doesn’t really sound like the “last examn” to me. But maybe it’s more the approach of coming up with good science questions. And not the exact dataset??
I think the easiest way to explain this, is to say they are testing the ability to reason your way to an answer, to a question so unique, that it doesn’t exist anywhere on the internet.