=Coffee

=Coffee

0 Ratings
0
Episode
146 of 147
Duration
56min
Language
English
Format
Category
Non-fiction

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


Listen and read

Step into an infinite world of stories

  • Read and listen as much as you want
  • Over 1 million titles
  • Exclusive titles + Storytel Originals
  • 7 days free trial, then €9.99/month
  • Easy to cancel anytime
Try for free
Details page - Device banner - 894x1036
Cover for =Coffee

Other podcasts you might like ...