“The second thing that they see is we typically discover agents that they had no idea were actually running in their environment.”
♫
Said on Smashing Security
“They're applying these models to the RL environments themselves… hack this environment… fixing those… lower rates of cheating downstream”
"The Cognitive Revolution" · AI:AM: A Level We Shouldn't Pass? Notes from The Curve + Tokens vs. Salaries & Is SaaS Cooked?
Play from 20:38
20:38
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
use models to hack their own RL environments, then fix the discovered flaws
Said nearby on the same subject
“We have a phrase we call the Moore's Law of RL environments, which basically means, like, every six to eight months, we've noticed that the complexity of the environment… roughly doubles.”
♫
Said on TBPN
“Hack The Box lets you appraise them, test them against realistic cybersecurity work, the way you'd test a new hire, and re-appraise them because the model changes, the tools change, the environments change”
♫
Said on Smashing Security
“Seed RL… was about utilizing the TPUs both for inference and training in the best possible way while keeping the environments as flexible as you wanted.”
♫
Said on Training Data
Moments like this, every Monday
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Track a competitor?
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.