Elad David

Posts by Elad David

• 
  Nov 9, 2026

  Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild

  A question the user never sees, an answer the model never gives, and a probe that catches more of what it never trained on.

  

  Elad David
• 
  Jun 4, 2026

  Your Model Reads Through Typos. Your Probe Doesn't.

  The Latent Undertow beneath fluent LLM behavior — and how to fish your activation probe out of it.

  

  Elad David