=Coffee

=Coffee

  • Autor
  • Osa
    • 146
  • Avaldatud
    • 16. veebr 2026
  • Kirjastaja
0 Hinnangud
0
Osa
146 of 148
Kestus
56 min
Keel
inglise
Vorming
Kategooria
Teadmiskirjandus

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


Loe ja kuula

Astu lugude lõputusse maailma

  • Suurim valik eestikeelseid audio- ja e-raamatuid
  • Proovi tasuta
  • Loe ja kuula nii palju, kui soovid
  • Lihtne igal ajal tühistada
Proovi tasuta
Device Banner Block-copy 894x1036
Cover for =Coffee

Muud podcastid, mis võivad sulle meeldida ...