=Coffee

=Coffee

0 Calificaciones
0
Episodio
146 of 148
Duración
56min
Idioma
Inglés
Formato
Categoría
No ficción

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


Escucha y lee

Descubre un mundo infinito de historias

  • Lee y escucha todo lo que quieras
  • Más de 1 millón de títulos
  • Títulos exclusivos + Storytel Originals
  • Precio regular: CLP 7,990 al mes
  • Cancela cuando quieras
Suscríbete ahora
Copy of Device Banner Block 894x1036 3
Cover for =Coffee

Otros podcasts que te pueden gustar...