10x More Efficient Pretraining

(magic.dev)

17 points | by meetpateltech 8 hours ago ago

2 comments

  • vkaku 7 hours ago ago

    I'd like to next the article which says almost no need for training models. That's really what I'm interested in at this point

  • aman_jha 7 hours ago ago

    insane work. maybe more companies can take on the OAI/ANT duopoly now (that are not google/meta)