Jay Alammar, Director at Cohere, discusses the practical adoption of Large Language Models in the enterprise. He covers the evolution of Retrieval-Augmented Generation (RAG) from a simple anti-hallucination tool to complex, agentic systems, the critical role of evaluation as intellectual property, and future trends like text diffusion and the increasing capability of smaller models for specialized business tasks.
Co-founder David shares Recall.ai's journey from a YC hackathon project to the essential data infrastructure for over 1,000 AI companies. He covers their strategic pivot to an API, the fundraising grind, and the lessons learned in building a lean, high-agency team that powers the future of AI with conversation data.
AI advocate Michelle Frost and consultant Hannes Lowette discuss the complex ethical landscape of AI development. They cover the value alignment problem, balancing competing values like accuracy versus fairness, the impact of recent US regulatory changes, and market disruptions from innovations like Deep Seek, ultimately calling for individual and corporate accountability to develop AI responsibly.
Edward, a founding engineer at Asteroid, discusses the critical challenge of managing catastrophic failures in agentic browser solutions, particularly in high-stakes domains like healthcare and insurance. He shares real-world examples of agent failures and outlines a practical framework for building more reliable, predictable, and accountable agents by scoping their capabilities, implementing robust human-in-the-loop tooling, and employing independent evaluation systems.
Krista Opsahl-Ong from Databricks introduces Agent Bricks, a platform designed to overcome the key challenges of productionizing enterprise AI agents. The talk covers common use cases, the difficult trade-offs between cost and quality, and how Agent Bricks uses automated evaluation and advanced optimization techniques to build cost-effective, high-performance agents.
This paper challenges the prevailing "bigger is better" narrative in AI, arguing that Small Language Models (SLMs) are not just sufficient but often superior for agentic AI tasks due to their efficiency, speed, and specialization. The discussion explores the paper's core arguments, counterarguments, and the practical implications of adopting a hybrid LLM-SLM approach.