Jim Fan of Nvidia outlines the endgame for robotics, arguing it will mirror the successful playbook of Large Language Models. He introduces "The Great Parallel," a roadmap where World Models replace Language Models, and data collection shifts from limited teleoperation to scalable egocentric video, culminating in a future of physical APIs and automated research.
Danilo Campos of PostHog details the common failure modes of LLM-based code generation—from model rot to security risks—and shares the practical, prose-driven strategies his team uses to make their autonomous coding agent reliable for thousands of users.
Cognitive psychologist Yanina Ledovaya explains how to boost developer productivity and satisfaction by focusing on three universal human needs from Self-Determination Theory: Autonomy, Competence, and Relatedness. This talk delves into how these psychological drivers underpin developer motivation, influence the adoption of AI tools, and provide a practical framework for managers to create more effective and engaging work environments.
Maggie Appleton from GitHub Next argues that current agentic tools are flawed by focusing on individual productivity, ignoring the collaborative nature of software development. She introduces ACE (Agent Collaboration Environment), a multiplayer platform designed to solve team alignment issues by integrating planning, development, and shared context in a real-time, sandboxed environment.
A deep dive with Sam Aaron, the creator of Sonic Pi, exploring his journey from early programming on a ZX Spectrum to creating a global platform for code-based music. The conversation covers the technical architecture of Sonic Pi, the critical role of Erlang's BEAM for concurrency, and the future direction with his new project, Tau5, which leverages AI for development and security testing.
Ekaterina Gorshkova, author of "Kafka for Architects", discusses her journey with Apache Kafka, from its early adoption in enterprise integration to its modern role as a foundational layer for AI and ML systems. The conversation covers key architectural decisions, the limitations of Kafka, and why the real challenges are often organizational rather than technical.