Zenity Labs logo
Zenity Labs
AI Agent Security Summit (On Demand)Join Us
Subscribe
  • Zenity Labs
  • Authors
  • Elad David
Elad David

Elad David

Your Model Reads Through Typos. Your Probe Doesn't.
3 hours ago

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
Elad David
Latest research, tools and talks about breaking and building AI systems, agents and assistants

Zenity Labs

Latest research, tools and talks about breaking and building AI systems, agents and assistants

Home

Posts

Authors

© 2026 Zenity Labs.

Privacy policy

Terms of use

Powered by beehiiv