Jeff Crume explores why humanities are crucial in an AI-driven world. While AI generates sophisticated answers, it lacks human understanding, purpose, and judgment. He argues that STEM fields explain 'how' but not 'why,' making humanities essential for ethical decision-making, interpreting AI outputs, understanding bias, and effective prompt engineering. Ultimately, AI amplifies the need for human critical thinking and judgment.
DSPy emphasizes separating task definition from model implementation using a "Signature" (inputs/outputs) to enable flexible, optimizable, and scalable AI programs. The framework relies on three pillars—instructions (specs), hard constraints (code), and examples (evals)—to fully specify tasks. DSPy 4.0 introduces DSPy Flex for learning program harnesses and Qualitative Learning for automated, feedback-driven evaluation refinement, offering significant benefits for enterprise applications and addressing "last-mile learning" for future AI systems.
This summary explores the evolving role of fine-tuning in modern AI workflows, comparing it with advanced techniques like RAG, LoRA, and enhanced generative AI capabilities. It discusses the historical benefits, current limitations due to rapidly advancing frontier models, and outlines a practical decision framework for customizing machine learning models and designing efficient AI systems.
AI teams are deploying advanced agent systems without the fundamental safety mechanisms (feature flags, canaries, kill switches) that web teams adopted over a decade ago. This oversight leads to critical incidents like data deletion and financial loss. This talk introduces six agent-specific feature flag types—for prompts, tools, models, memory, autonomy, and sub-agents—and outlines a practical playbook for secure AI deployment, emphasizing the critical role of a pre-wired kill switch to manage the high blast radius of AI agents.
Philipp Schmid from Google DeepMind emphasizes the critical, often-overlooked need for rigorous evaluation of AI agent skills. He argues that shipping skills without testing is akin to deploying code without unit tests, leading to unreliable agent behavior. The talk covers what defines an agent skill, strategies for writing effective and correctly triggering skills, and a practical guide to building lightweight evaluation harnesses to catch failures proactively.
Steve Mock, investor and entrepreneur, discusses aisavedme.org, a platform born from his father's question, "How does one use AI?". The site gathers real-world stories of AI's positive impact, revealing surprising human outcomes in healthcare, education, and personal fulfillment, often less about technology and more about connection. He also shares his unique no-code journey in building the site and his venture capital insights into the "data flywheel" and "vertical AI" as key to successful investments.