Professor Hannah Fry speaks with Jack Parker-Holder and Shlomi Fruchter about Genie 3, a general-purpose world model that generates diverse, interactive environments from prompts. The discussion covers its auto-regressive nature, which enables the creation of consistent, explorable worlds, its key differences from video models like Veo, and its foundational role in training AI agents and advancing toward AGI.
Eoghan McCabe, founder and CEO of Intercom, shares the unfiltered story of transforming a multi-billion dollar, stagnating SaaS business into a rapidly growing, AI-first company. He details the necessity of 'founder mode,' a radical cultural overhaul, and why having nothing to lose is the ultimate advantage in the AI era.
This talk addresses the unreliability of current AI agents, arguing that prompting is insufficient. It posits that Reinforcement Learning (RL) is the most promising solution, delving into the mechanisms of RLHF and RLVR. The core challenge identified is 'reward hacking', and the discussion explores future directions to overcome it, such as RLAIF, data augmentation, and the development of interactive, online models that can learn in real-time.
Drawing from conversations with top AI builders, Dex argues that production-grade AI agents are not magical loops but well-architected software. This talk introduces "12-Factor Agents," a methodology centered on "Context Engineering" to build reliable, high-performance LLM-powered applications by applying rigorous software engineering principles.
This talk introduces Eval-Driven Development (EDD) as a scientific alternative to 'vibe-based' iteration for improving AI agents. It covers quantitative evaluation (choosing strong end-to-end metrics, aligning LLM judges) and qualitative evaluation (using error and attribution analysis to debug failures), providing a structured framework for consistent agent improvement.
Robert from Emergent Methods discusses how grounded synthetic news data can solve the publisher revenue crisis in the AI era. He details the process of 'Context Engineering' news into token-optimized, objective data for high-stakes AI agent tasks, covering their open-source models for entity extraction and bias mitigation, and the on-premise infrastructure that protects publisher content.