dweinberger,
@dweinberger@mastodon.social avatar

Here is the link to the article @garymarcus
discusses that argues that the relationship between training set size and improvements in models' performance is non-linear in the wrong direction. https://arxiv.org/abs/2404.04125

  • All
  • Subscribed
  • Moderated
  • Favorites
  • ai
  • rosin
  • thenastyranch
  • ethstaker
  • osvaldo12
  • mdbf
  • DreamBathrooms
  • InstantRegret
  • magazineikmin
  • Youngstown
  • ngwrru68w68
  • slotface
  • GTA5RPClips
  • kavyap
  • cubers
  • JUstTest
  • everett
  • cisconetworking
  • tacticalgear
  • anitta
  • khanakhh
  • normalnudes
  • Durango
  • modclub
  • tester
  • provamag3
  • Leos
  • megavids
  • lostlight
  • All magazines