"The Cognitive Revolution"
"The Cognitive Revolution"
Erik Torenberg, Nathan Labenz
GELU, MMLU, & X-Risk Defense in Depth, with the Great Dan Hendrycks
2 hour 35 minutes Posted Oct 19, 2024 at 7:28 am.
Join Nathan for an expansive conversation with Dan Hendrycks, Executive Director of the Center for AI Safety and Advisor to Elon Musk's XAI. In this episode of The Cognitive Revolution, we explore Dan's groundbreaking work in AI safety and alignment, from his early contributions to activation functions to his recent projects on AI robustness and governance. Discover insights on representation engineering, circuit breakers, and tamper-resistant training, as well as Dan's perspectives on AI's impact on society and the future of intelligence. Don't miss this in-depth discussion with one of the most influential figures in AI research and safety.Check out some of Dan's research papers:MMLU: https://arxiv.org/abs/2009.03300GELU: https://arxiv.org/abs/1606.08415Machiavelli Benchmark: https://arxiv.org/abs/2304.03279Circuit Breakers: https://arxiv.org/abs/2406.04313Tamper Resistant Safeguards: https://arxiv.org/abs/2408.00761Statement on AI Risk: https://www.safe.ai/work/statement-on-ai-riskApply to join over 400 Founders and Execs in the Turpentine Network: https://www.turpentinenetwork.co/SPONSORS:Shopify: Shopify is the world's leading e-commerce platform, offering a market-leading checkout system and exclusive AI apps like Quikly. Nobody does selling better than Shopify. Get a $1 per month trial at https://shopify.com/cognitive.LMNT: LMNT is a zero-sugar electrolyte drink mix that's redefining hydration and performance. Ideal for those who fast or anyone looking to optimize their electrolyte intake. Support the show and get a free sample pack with any purchase at https://drinklmnt.com/tcr.Notion: Notion offers powerful workflow and automation templates, perfect for streamlining processes and laying the groundwork for AI-driven automation. With Notion AI, you can search across thousands of documents from various platforms, generating highly relevant analysis and content tailored just for you - try it for free at https://notion.com/cognitiverevolutionOracle: Oracle Cloud Infrastructure (OCI) is a single platform for your infrastructure, database, application development, and AI needs. OCI has four to eight times the bandwidth of other clouds; offers one consistent price, and nobody does data better than Oracle. If you want to do more and spend less, take a free test drive of OCI at https://oracle.com/cognitiveCHAPTERS:
Teaser
About the Show
About the Episode
Intro
GELU Activation Function
Signal Filtering
Scaling Maximalism
Sponsors: Shopify | LMNT
New Architectures
AI as Complex System
The Machiavelli Benchmark
Sponsors: Notion | Oracle
Understanding MMLU Scores
Reasoning in Language Models
Multimodal Reasoning
World Modeling and Sora
Arc Benchmark and Hypothesis
Humanity's Last Exam
Benchmarks and AI Ethics
Robustness and Jailbreaking
Representation Engineering
Convergence of Approaches
Circuit Breakers
Tamper Resistance
Interpretability vs. Robustness
Open Source and AI Safety
Computational Irreducibility
Neglected Approaches
Truth Maxing and XAI
AI-Powered Forecasting
Chip Bans and Geopolitics
Working at CAIS
Extinction Risk Statement
0:00
2:35:31
Download MP3
Show notes
Join Nathan for an expansive conversation with Dan Hendrycks, Executive Director of the Center for AI Safety and Advisor to Elon Musk's XAI. In this episode of The Cognitive Revolution, we explore Dan's groundbreaking work in AI safety and alignment, from his early contributions to activation functions to his recent projects on AI robustness and governance. Discover insights on representation engineering, circuit breakers, and tamper-resistant training, as well as Dan's perspectives on AI's impact on society and the future of intelligence. Don't miss this in-depth discussion with one of the most influential figures in AI research and safety.Check out some of Dan's research papers:MMLU: https://arxiv.org/abs/2009.03300GELU: https://arxiv.org/abs/1606.08415Machiavelli Benchmark: https://arxiv.org/abs/2304.03279Circuit Breakers: https://arxiv.org/abs/2406.04313Tamper Resistant Safeguards: https://arxiv.org/abs/2408.00761Statement on AI Risk: https://www.safe.ai/work/statement-on-ai-riskApply to join over 400 Founders and Execs in the Turpentine Network: https://www.turpentinenetwork.co/SPONSORS:Shopify: Shopify is the world's leading e-commerce platform, offering a market-leading checkout system and exclusive AI apps like Quikly. Nobody does selling better than Shopify. Get a $1 per month trial at https://shopify.com/cognitive.LMNT: LMNT is a zero-sugar electrolyte drink mix that's redefining hydration and performance. Ideal for those who fast or anyone looking to optimize their electrolyte intake. Support the show and get a free sample pack with any purchase at https://drinklmnt.com/tcr.Notion: Notion offers powerful workflow and automation templates, perfect for streamlining processes and laying the groundwork for AI-driven automation. With Notion AI, you can search across thousands of documents from various platforms, generating highly relevant analysis and content tailored just for you - try it for free at https://notion.com/cognitiverevolutionOracle: Oracle Cloud Infrastructure (OCI) is a single platform for your infrastructure, database, application development, and AI needs. OCI has four to eight times the bandwidth of other clouds; offers one consistent price, and nobody does data better than Oracle. If you want to do more and spend less, take a free test drive of OCI at https://oracle.com/cognitiveCHAPTERS:(00:00:00) Teaser(00:00:48) About the Show(00:02:17) About the Episode(00:05:41) Intro(00:07:19) GELU Activation Function(00:10:48) Signal Filtering(00:12:46) Scaling Maximalism(00:18:35) Sponsors: Shopify | LMNT(00:22:03) New Architectures(00:25:41) AI as Complex System(00:32:35) The Machiavelli Benchmark(00:34:10) Sponsors: Notion | Oracle(00:37:20) Understanding MMLU Scores(00:45:23) Reasoning in Language Models(00:49:18) Multimodal Reasoning(00:54:53) World Modeling and Sora(00:57:07) Arc Benchmark and Hypothesis(01:01:06) Humanity's Last Exam(01:08:46) Benchmarks and AI Ethics(01:13:28) Robustness and Jailbreaking(01:18:36) Representation Engineering(01:30:08) Convergence of Approaches(01:34:18) Circuit Breakers(01:37:52) Tamper Resistance(01:49:10) Interpretability vs. Robustness(01:53:53) Open Source and AI Safety(01:58:16) Computational Irreducibility(02:06:28) Neglected Approaches(02:12:47) Truth Maxing and XAI(02:19:59) AI-Powered Forecasting(02:24:53) Chip Bans and Geopolitics(02:33:30) Working at CAIS(02:35:03) Extinction Risk Statement(02:37:24) Outro