News for hackers. Stuff that matters.
Re:Lila: A Unified Benchmark for Mathematical Reasoning by vladharbuz on Saturday December 31, 2022 @03:27AM (#34194679)
It would have been nice to have a list with an example for each of the 23 tasks. Have I missed it?
Re:Lila: A Unified Benchmark for Mathematical Reasoning by DataDaoDe on Saturday December 31, 2022 @03:56AM (#34194793)
They have a lot of examples in the appendix, just scroll to after the references.
Re:Lila: A Unified Benchmark for Mathematical Reasoning by Someone on Saturday December 31, 2022 @08:19AM (#34196195)
On page 24, figure 6 right, I think the “gold answer” is incorrect. It should be 160. It may have been copy-paste-not edited from the gold answer on page 22, figure 4 right.
Re:Lila: A Unified Benchmark for Mathematical Reasoning by c7b on Saturday December 31, 2022 @11:58AM (#34198277)
Seeing those insane advances really makes me itch to go back into academia. AI that can do math really feels like we're about to crack 'it'.