Controlling AI Models from the Inside
From Practical AI · · 43 min
This plays from the publisher's own server. We do not host a copy.
Description
As generative AI moves into production, traditional guardrails and input/output filters can prove too slow, too expensive, and/or too limited. In this episode, Alizishaan Khatri of Wrynx joins Daniel and Chris to explore a fundamentally different approach to AI safety and interpretability. They unpack the limits of today’s black-box defenses, the role of interpretability, and how model-native, runtime signals can enable safer AI systems.
Featuring:
- Alizishaan Khatri – LinkedIn (https://www.linkedin.com/in/alizishaan-khatri-32a20637/)
- Chris Benson – Website (https://chrisbenson.com/), LinkedIn (https://www.linkedin.com/in/chrisbenson), Bluesky (https://bsky.app/profile/chrisbenson.bsky.social), GitHub (https://github.com/chrisbenson), X (https://x.com/chrisbenson)
- Daniel Whitenack – Website (https://www.datadan.io/), GitHub (https://github.com/dwhitena), X (https://x.com/dwhitena)
Upcoming Events:
- Register for upcoming webinars here (https://practicalai.fm/webinars)!