In a live demo, Poolside's CEOs showcase their second-generation model, the Malibu agent, by migrating a complex codebase from ADA to Rust, including automated testing and iterative feature development. They outline their vision for achieving AGI through a full-stack approach combining proprietary models, reinforcement learning, and massive-scale compute, with plans for a public model release in early 2025.
This talk provides a practical framework for product managers to move beyond simple "vibe checks" to implement rigorous, data-driven evaluation for LLM-powered products. Using a live demo of a multi-agent AI trip planner, the speaker breaks down essential methodologies, including human feedback, code-based checks, and LLM-as-a-judge systems, and demonstrates how to iterate on both prompts and the evals themselves to ensure consistent quality and build user trust.
An unofficial deep dive into the architecture of modern coding agents like Claude Code. Jared Zoneraich of PromptLayer explains the shift towards simpler, model-centric designs, detailing the core components like the master loop, tool calling (especially `bash`), and context management strategies. The talk also contrasts Claude's philosophy with other agents like Codex, AMP, and Cursor, offering practical takeaways for building your own AI agents.
Experts from a16z outline three transformative ideas for 2026. Ryan McEntush discusses the rise of the 'electro-industrial stack' and the critical need for the U.S. to build a supportive industrial ecosystem. Angela Strange explains why financial services are at a tipping point, with AI-native platforms set to replace legacy systems, unify data, and create 10x winners. Sarah Wang predicts the emergence of a 'dynamic agent layer' that will overtake traditional systems of record by collapsing the gap between user intent and execution.
Experts from a16z forecast three major AI-driven shifts for 2026. Ryan McEntush discusses the rise of the 'electro-industrial stack' and the need for a U.S. ecosystem to power modern industry. Angela Strange explains how financial services are at a tipping point, with AI-native platforms unifying data to unlock massive efficiency gains. Sarah Wang predicts that a 'dynamic agent layer' will overtake traditional systems of record, fundamentally changing enterprise software by directly translating user intent into action.
Fabrizio Romano, author of "Learning Python Programming," discusses the evolution of his book with Naomi Ceder. Key topics include the strategic shift from GUIs to CLIs, the evolving perspective on Python's type hinting, and the dual role of AI as a powerful tool and a potential threat to junior developer growth. Fabrizio emphasizes the importance of fundamental skills, mentorship, and the human element in the age of AI.