MIT Technology Review got an exclusive preview of the research
The article was published 3 days after the arxiv release. How is this an “exclusive preview”?
Successfully tricking existing models by a few crafted samples doesn’t seem like a significant achievement. Can someone highlight what exactly is interesting here? Anything that can’t be resolved by routine adjustments to loss/evaluation functions?
Several Dutch people told me that firearms are common on ships under the Dutch flag. Given the number of people owning sea-worthy vessels this might be interesting. Do you know anything about this?