Ari Weinstein discusses how Codex's 'computer use' feature allows the AI agent to operate local Mac applications in the background by combining multimodal vision with accessibility data, enabling non-intrusive, parallel task execution.
Nico Albanese from Vercel demonstrates how to build a stateful, learning AI agent from scratch using AI SDK v6. The workshop covers the core components: a tool loop, provider-executed tools like web search, end-to-end type safety, and Vercel's new persistent named sandboxes, which give the agent a file system to persist state, memory, and even self-generated tools across sessions.
95% of GenAI pilots fail due to feedback integration issues, not deployment challenges. Alessandro Cappelli argues that Reinforcement Learning (RL) provides the only systematic way to incorporate business metrics and production signals to continuously improve models, especially for complex agent-based systems.
Vincent Koc argues that static benchmarks are failing in the era of adaptive AI. He proposes a shift from static testing to 'malleable evals,' where agents self-optimize and curate their own test suites based on user intent and production data, treating evaluation as a living, evolving system.
Lloyd Blankfein, former CEO of Goldman Sachs, shares insights on leadership in crisis, the philosophy of risk management, and the evolution of institutional culture. He discusses navigating the 2008 financial crisis, the transition from a partnership to a public company, and the profound impact of technology and AI on finance and risk.
Explore the evolution of AWS Lambda and the serverless ecosystem over the last decade, focusing on the two core pillars that have revolutionized the developer journey: Developer Experience (DevEx) and Observability. This session covers the shift from console-based workflows to modern IDE-integrated development, the role of tools like Lambda Layers and Extensions, and the importance of the broader serverless landscape including AWS Step Functions.