We turn high signal in-person events for the top AI engineers, founders, leaders, and researchers in the world into the best free learning opportunities for millions around the world here on YouTube. Your subscribes, likes, comments, speaking, attendance, or sponsorships goes a long way toward making our biz model sustainable indefinitely. We strongly believe this industry deserves a better class of community and that we know how to do this well; we just need your support.
Effective marketplace discovery relies on deep semantic understanding rather than simple engagement optimization. DoorDash integrates Large Language Models (LLMs) into its search and recommendation systems through four core primitives: LLM-based supervision, semantic catalog IDs, consumer memory blocks, and steerable c...
AI Engineer Paris 2026 explores the technical and economic frontiers of generative AI, focusing on infrastructure, model efficiency, and agentic workflows. Presenters detail advancements in customizing foundational models like Flux for robotics and action prediction, alongside strategies for scaling voice AI through re...
AI integration into the economy follows historical patterns of general-purpose technologies, where significant productivity gains emerge only after long periods of organizational and infrastructure adaptation. Current AI development is transitioning from experimental "vibe coding" toward rigorous "software factories" t...
Building effective AI agents requires moving beyond simple RAG-based information synthesis toward robust, multi-step agentic workflows that handle unstructured, multimodal data. PDFs remain a significant bottleneck due to their complex, legacy formats, necessitating a hybrid approach that combines traditional computer ...
Skill engineering requires moving beyond basic prompting toward "harness engineering," where developers extend an AI agent's capabilities through scripts, hooks, and multi-agent architectures. Relying on prose instructions is insufficient because models naturally gravitate toward generic, overfitted outputs. Instead, d...
RMS norm layers in transformer architectures often create performance bottlenecks due to frequent memory communication and inefficient GPU utilization. By applying algebraic optimizations—specifically weight folding, deferred normalization, and pre-normalization cancellation—computational overhead significantly decreas...
Stateful LLM inference systems often fail silently, producing high-confidence gibberish rather than explicit errors. Debugging these issues requires moving beyond standard crash logs to forensic analysis of log-probabilities and kernel behavior. Two critical failures in the Jamba model’s Mamba architecture illustrate t...
Follow this podcast in Podwise
Sign in to get AI summaries, transcripts and mind maps for any episode, including new ones.
