=Coffee

=Coffee

0 Recensioner
0
Episod
146 of 147
Längd
56min
Språk
Engelska
Format
Kategori
Fakta

A lot of modern AI models have a kind of security guard layer that sits in front of them. Its job? A binary choice as to whether the prompt heading into the model is safe or not. Kasimir Schulz, a lead security researcher at HiddenLayer, has been researching how to trick these models. Their solution, a technique called "Echogram" involves words with such positive statistical sentiment — such overwhelming good vibes — that it flips that verdict.

Learn more about your ad choices. Visit podcastchoices.com/adchoices


Lyssna när som helst, var som helst

Kliv in i en oändlig värld av stories

  • 1 miljon stories
  • Hundratals nya stories varje vecka
  • Få tillgång till exklusivt innehåll
  • Avsluta när du vill
Starta erbjudandet
SE - Details page - Device banner - 894x1036
Cover for =Coffee

Andra podcasts som du kanske gillar...