While I'm enjoying the discussion of adversarial examples on Twitter, I wish this could have taken place earlier on OpenReview. We need a better mechanism for post-publication peer review and correction in the modern age. Maybe GitHub? (https://github.com/anishathalye/obfuscated-gradients/issues/2 …)
-
-
The people who need rate limiting seem to be a small minority, who are easily enough blocked :)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.