Nilesh Trivedi 2024-06-15 04:51:50 This is an AGI benchmark where LLMs currently perform 34%. A prize has been announced for the first team to reach 85% performance: arcprize.org
Oleksandr Kryvonos 2024-06-15 16:29:18 it is very interesting, for now I keep my self with the illusion that I can create an Intelligent System that can pass such test, anyhow it will be either disilusional cold shower or I will get 125k of prize