ABOUT THIS EPISODE
On the very first episode of Hidden Context, HiddenLayer’s Director of Adversarial Research Jason Martin joins Jim to talk about everything from Jev to KROP to how he got such a fancy job title for a job where he gets to break stuff all day. (Please note that this conversation was recorded before October 22, which is why the OpenAI Decisions API is referred to as a preview.)
References include Daniel Kahneman’s Thinking, Fast and Slow, The Matrix, Mr. Robot, and Little Bobby Tables.
Other mentions include the AWS Strands Decider, OpenAI Decisions API, and Cloudflare Clef.
For further reading on Jason’s deep-dive into KROP, check out our blog post Boosting Security for AI: Unveiling KROP.
English
United States
IN THIS EPISODE
TRANSCRIPT 🔗
JASON MARTIN: In the forecast, it's cloudy with a chance of system one models being a part of every model release from this point forward.
JIM SIMPSON: Welcome to "Hidden Context," the podcast about the weirdly specific ways that AI can go wrong, and what that means now that we're quietly started trusting it with pretty much everything. I'm Jim Simpson, an intel analyst at HiddenLayer, and every episode I'm gonna sit down with somebody considerably cleverer than me.
The way in which the show's…
JIM SIMPSON: Welcome to "Hidden Context," the podcast about the weirdly specific ways that AI can go wrong, and what that means now that we're quietly started trusting it with pretty much everything. I'm Jim Simpson, an intel analyst at HiddenLayer, and every episode I'm gonna sit down with somebody considerably cleverer than me.
The way in which the show's…
Disclaimer: The podcast and artwork embedded on this page are from HiddenLayer, which is the property of its owner and not affiliated with or endorsed by Listen Notes, Inc.
EDIT
Thank you for helping to keep the podcast database up to date.