30초 요약
The speakers discuss jailbreak robustness and long-tail failures in language models used as judges. The speaker argues that subtle failures may still matter and that human supervision can be warranted.
- 1RobustnessGreater robustness does not imply failures have disappeared.
- 2Long-tail failuresSubtle failures can still matter.
- 3SupervisionAutomated judging requires evaluation and may need human supervision.
핵심 정리
- Greater robustness does not imply failures have disappeared.
- Subtle failures can still matter.
- Automated judging requires evaluation and may need human supervision.
챕터별로 다듬은 전문 읽기
Limits of automated evaluation
The speaker discusses failure modes and oversight.
The interviewer asks how to interpret claims that a model is more robust to jailbreaks: do obvious failures remain, or have the remaining cases become more subtle?
The speaker says mitigation can make failures subtler, but subtle does not mean harmless. Language models used as judges can have unusual, long-tail failure cases, as can refusal mechanisms.
There is a tradeoff between compute spent on an automated judge and its accuracy. The speaker says failures can still warrant human supervision; the clip does not quantify an error rate or define a universally safe threshold.
같은 채널의 다른 글
1:49:40EN
Cognitive Revolution "How AI Changes Everything"· 2026년 10월 28일팟캐스트 · 4명A Strategy for Preserving Options on the Path to Advanced AI게스트 Joel Predd, Ben Boudreaux, Matt Chessen · 진행자 Nathan LabenzRAND researchers discuss uncertainty, security architecture and human agency with Nathan Labenz.
1:28:36ENCognitive Revolution "How AI Changes Everything"· 2026년 10월 24일팟캐스트 · 5명AI’s Pace: Interpretability, GPU Credit and the Physical Supply Chain게스트 Zvi Mowshowitz, Evan Conrad, Lonis Hamaili · 진행자 Nathan Labenz, Prakash NarayananA weekly highlights episode weighs uncertain AI research trajectories against finance, infrastructure, security and regulation.
3:13:44ENCognitive Revolution "How AI Changes Everything"· 2026년 10월 22일팟캐스트 · 4명AI’s Physical Bottlenecks: Compute Markets, Chip Investments and Agent Trust게스트 Evan Conrad, Lonis Hamaili · 진행자 Nathan Labenz, Prakash NarayananA full AI:AM discussion of security incidents, GPU financing, semiconductor supply and an agent-to-agent network.
2:40:58ENCognitive Revolution "How AI Changes Everything"· 2026년 10월 21일팟캐스트 · 3명Frontier AI, Interpretability and the Fight Over Its Pace게스트 Zvi Mowshowitz · 진행자 Nathan Labenz, Prakash NarayananZvi Mowshowitz joins AI:AM to discuss neural networks, policy and the institutions facing rapid change.
1:25:56ENCognitive Revolution "How AI Changes Everything"· 2026년 10월 17일팟캐스트Claude Changed the Password. The Steering Wheel Was Already Optional진행자 Nathan LabenzNathan Labenz and Prakash Narayanan spend a week on agents that can lock you out, models that dodge a feeling they deny having, and formal proofs that found Linux bugs.
2:51:22ENCognitive Revolution "How AI Changes Everything"· 2026년 10월 14일팟캐스트 · 4명AI Minds and 8 mm Memories: Research, Archives and Simulation게스트 Cameron Berg, Phil Maher · 진행자 Nathan Labenz, Prakash NarayananCameron Berg discusses hidden model states; Phil Maher explains preserving home movies and a fly-brain demo.