upcarta
  • Sign In
  • Sign Up
  • Explore
  • Search
Mentions
Peter Wang @pwang · Apr 6, 2023
  • From Twitter

Fantastic thread. We need to get better at handholding, so we know when *we’ve* let go and the model is pedaling on its own. (And to be clear: our current ways of handholding may actually be training wheels, and not handholding at all.)

Tweet Apr 6, 2023
It obviously matters, because it has implications to how well the models can generalize to never-before-seen inputs and tasks. Serious exacerbation of automation bias can occur if we ascribe reasoning to what is just a minor perturbation of training
by Talia Ringer
Post Add to Collection Mark as Completed
Recommended by 1 person
1 mention
Share on Twitter Repost
  • upcarta ©2025
  • Home
  • About
  • Terms
  • Privacy
  • Cookies
  • @upcarta