A Chinese AI model will score over 85% on the MMLU before 2024
NathanpmYoung avatar
Nathan Young
6
closes 2024
30%
chance

Get Ṁ500 play money

Related questions

Will a large language model beat a super grandmaster playing chess by 2028?
MP avatarMP
47% chance
By the end of 2026, will we have transparency into any useful internal pattern within a Large Language Model whose semantics would have been unfamiliar to AI and cognitive science in 2006?
EliezerYudkowsky avatarEliezer Yudkowsky
62% chance
Will a 10B parameter multimodal RL model be trained by Deepmind in the next 12 months?
BionicD0LPH1N avatarBionic
66% chance
HumanEval 90% #1: Will pass@1 performance on the HumanEval benchmark be >= 90% by 2024?
vluzko avatarVincent Luczkow
69% chance
Will there be a Forward-Forward Algorithm based neural network with >65% Top 1 Accuracy on Papers With Code's ImageNet leaderboard by 2024?
l8doku avatarl8doku
28% chance
Will reinforcement learning overtake LMs on math before 2028?
JacobPfau avatarJacob Pfau
38% chance
Will a model costing >$30M be intentionally trained to be more mechanistically interpretable by end of 2027? (see desc)
NoaNabeshima avatarNoa Nabeshima
58% chance
When will tinygrad train its first MLPerf qualifying model?
GeorgeHotz avatarGeorge Hotz
🐕 Will AI Achieve Significantly More, "Embodiment" by end of 2023?
PatrickDelaney avatarPatrick Delaney
42% chance
Will we learn by EOY 2024 that large AI labs use something like activation addition on their best models?
JSD avatarJSD
32% chance
By 2025 end, a model exhibits action recognition (video) equivalent to human level accuracy on Something Something V2?
firstuserhere avatarfirstuserhere
58% chance
Will language models be able to solve simple graphical mazes by the end of 2025?
Benx avatarBenx
48% chance
Will a news article containing the string "love in the time of large language models" be published in 2023
tftftftftftftftftftftftf avatarTessa B
26% chance
Short Term AI 2.3: By January 2024, will SOTA on MATH minival be >= 85%?
vluzko avatarVincent Luczkow
71% chance
Will Transformer based architectures still be SOTA for language modelling by 2026?
LeoGao avatarLeo Gao
66% chance
Will more than 20 organizations publicly train large language models by 2024?
vluzko avatarVincent Luczkow
10% chance
By 2030, will large language models still be at the peak of AI? [DRAFT]
tailcalled avatartailcalled
34% chance
Will a new best accuracy for ImageNet classification be achieved before the end of 2023?
Widden avatarWidden
49% chance
Will Metaculus have built-in support for reflective latent variables by 2025?
tailcalled avatartailcalled
45% chance
Will anyone train a 50B parameter+ RetNet by the end of 2023?
vluzko avatarVincent Luczkow
32% chance
1 Comments
6 Positions
7 Trades
Sort by:
TaoLin avatar
Tao Lin

How worried should we be about a chinese lab training on the answers, declaring they've solved MMLU, and not releasing the model so people can't tell they cheated?