Merve Noyan from Hugging Face discusses how open-source models have achieved parity with closed-source counterparts, highlighting the Hugging Face ecosystem built to support this shift. She covers tools for model selection, local agent deployment, and the transformative "Hugging Face Skills" that allow agents to automate complex ML engineering tasks like fine-tuning models with a single prompt.
In a live panel at the Physical AI Builders Forum, founders and operators in computer vision, robotics, and multimodal AI share their 2026 playbooks. The discussion covers the architectural differences between physical and generative AI, the strategic shift from frame AI to scene AI for enterprise value, and the critical skills needed to build and scale a modern AI business.
Erin Price-Wright, Turner Caldwell (Mariana Minerals), and Drew Baglino (Heron Power) discuss closing America's critical minerals gap and modernizing the power grid for the AI economy. They cover how automation, reinforcement learning, and lessons from Tesla can accelerate mining, refining, and grid infrastructure development to compete with China and enable re-industrialization.
Madison Faulkner and Hugo Santos explain why traditional CI/CD, built for human developers, is failing under the load of AI agents. They propose a new paradigm of 'Continuous Compute' centered on intent-driven agent loops, fast inline validation, and a pre-merge layer where humans review outcomes, not diffs, paving the way for a 'multiverse' of parallel development.
Anton Arhipov from JetBrains introduces Koog, a lightweight, Kotlin-native framework for building tool-using LLM agents. This session covers the rationale for using Kotlin in AI, the architecture of Koog agents, and how its graph-based DSL enables the creation of structured, type-safe, and reproducible agent workflows, moving beyond simple prompt-chaining to sophisticated orchestration.
Experts discuss the rise of LLMjacking, where stolen AI API keys lead to massive financial losses. They explore how AI is reshaping adversary simulations, the enduring need for human expertise in the loop, and the debate over accelerating security patch timelines in the face of AI-powered threats.