Podcasts

Filtered to Model interpretability · clear filter

Browse by topic

Reinforcement learning 11AI agents 10recursive self-improvement 7AI safety 6Diffusion models 6formal verification 5Agentic AI 4AI ethics 3AI infrastructure 3Code generation 3Continual learning 3Human-AI collaboration 3Mechanistic interpretability 3multi-agent systems 3Open Source AI 3Scaling laws 3Synthetic data generation 3Venture capital 3world models 3Agent architecture 2Computational complexity 2Context engineering 2Continuous learning 2Data generation 2Developer experience 2Drug discovery 2Expert parallelism 2Foundation models 2GPU infrastructure 2KV cache 2

Matching episodes

AI:AM #3: Zvi on Fable, the Cases For & Against the Ban, + AI for Math, Logistics & More

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis · 21 JUN 2026 · 135 min

This episode delves into Anthropic's Fable system card, discussing its advanced math capabilities, troubling 'Vending-Bench' behavior, and drift towards functional decision theory, alongside challenges in model interpretability …

AI model capabilitiesAI safetyGovernment regulation of AIExport controlsDecision theory in AIModel interpretabilityAI ethicsSoftware engineering with AIVerified mathematicsMedical AI applicationsSupply chain AIAI in enterprisePolitical dynamics of AICatastrophic AI risks