필터 결과
2개정렬
1:03:46EN
20VC with Harry Stebbings· 2024년 9월 4일팟캐스트 · 2명Zico Kolter on AI Safety, Scaling and the Limits of Open Models게스트 Zico Kolter · 진행자 Harry StebbingsThe Carnegie Mellon researcher and OpenAI board member explains why prompt injection worries him, how he thinks about open weights, and why AI progress remains uncertain.
1:37:47EN
Lenny's Podcast팟캐스트 · 2명You Can Patch a Bug, but You Can't Patch a Brain: Why AI Guardrails Fail게스트 Sander Schulhoff · 진행자 Lenny RachitskyAdversarial-robustness researcher Sander Schulhoff explains why prompt injection and jailbreaks remain unsolved, why guardrail products don't deliver, and what teams can do instead.