All videosAI security0:48

Poisoning

What happens when a document or memory preserves a dangerous instruction and the system uses it again later.

Links containing ?t= open the video at a specific second.

Video summary

The ideas to retain

01

Storing a datum does not make it true

Storing an output in a database does not make it trustworthy. An agent's memory should have an origin, date, scope, permissions and an expiration policy. Without those properties, the…

02

Persistent memory is already a measurable attack surface

Evidence from 2026 makes it possible to analyze this surface much more directly than the earliest work on backdoors in model weights.

03

Dangerous behavior can also remain hidden in the model

The Sleeper Agents study built test models that wrote safe code when the prompt indicated 2023 and vulnerable code when it indicated 2024. The demonstration does not describe a commercial…