Our readingWhat is a korrent?
HellaSwag is largely solved by today's language models; the remaining few percent are probably dataset errors or very hard questions.
Drawn from what Andrej Karpathy said
Our readingWhat is a korrent?
Drawn from what Andrej Karpathy said
basically the 4% the last 4% is probably errors in the data set or the questions are really really hard and so basically this data set is kind of crushed with respect to language models
Where this was said
Watch from 3:31:11 plays here↗Let's reproduce GPT-2 (124M)youtube.com
All 14 korrents from this recordingthis one is 13th
Added to korrents 9 Nov 2026 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
I hold this tooShared subject first, then similar wording. They may agree or disagree.