Videos

This video provides an in-depth exploration of how to build AI agents capable of running for several hours without losing focus or coherence. Presented by engineers from Anthropic, the talk covers the transition from basic model prompting to sophisticated multi-agent harness designs that utilize a Planner-Generator-Evaluator loop. Viewers will learn about the history of the Claude model series and the specific engineering techniques used to overcome context rot, planning failures, and self-evalu...

The video features a deep dive fireside chat between Meta's Jesse Chen and Anthropic's Boris Cherny regarding the current state and future trajectory of AI in software engineering. They discuss the transition from using AI as a simple assistant to employing autonomous agents and loops that can handle complex end to end tasks like code maintenance, security patching, and even project management. The discussion specifically covers the evolution of Claude models, the launch of Claude Code, and the ...

Loop engineering is a revolutionary approach to artificial intelligence that replaces manual prompting with autonomous systems that allow AI to prompt itself and iterate until a goal is met. This video explores how leaders in the AI space are moving away from traditional chatbot interactions to design complex loops where the human sets the initial objective and then allows a fleet of specialized agents to discover, plan, execute, and verify the work. This methodology is particularly powerful for...

Voicebox is a powerful open source AI voice studio that allows users to clone voices, generate high quality speech across multiple engines, and perform system wide dictation entirely on local hardware. As a local first alternative to cloud based giants like ElevenLabs, it provides developers and creators with full control over their data, privacy, and costs while offering advanced features like Model Context Protocol integration for AI agents. This video serves as an introductory guide and revie...

The video tutorial explores the creation of a cinematic, scroll-driven website for a brand named BurgerLab using the Claude Fable 5 model from Anthropic and the Higgsfield AI creative platform. This comprehensive guide covers the entire pipeline, including the initial project planning phase, the connection of external tools through the Model Context Protocol, the generation of custom image and video assets, and the final coding of a React-based website featuring sophisticated animations. It high...

Autoresearch is an innovative autonomous framework released by Andrej Karpathy that utilizes AI agents to continuously improve code, marketing assets, and business processes through a self-reinforcing loop of hypothesis creation, experimental testing, and objective scoring. Originally developed for optimizing machine learning models, this system has transitioned into a powerful tool for general business growth, allowing for thousands of iterations to occur without human intervention. This articl...

This video provides a deep dive into the capabilities of Claude Fable 5, the latest powerhouse model from Anthropic, and explains how to leverage it to build a robust AI Operating System (AIOS). The presentation moves beyond simple prompting, showing viewers how to create a centralized, folder-based architecture that acts as a second brain for their personal and professional lives. By integrating context, live data connections, and specialized skills, users can transform Claude into a proactive ...

This video covers the strategic roadmap for building and scaling a high-value AI consulting agency in the era of agentic workflows. Devin Kearns explains the transition from simple AI automations to integrated production systems that provide measurable ROI, focusing on serving the mid-market to maximize enterprise value and prepare for a significant business exit. ## Key Takeaways * Pure development value is trending toward zero as AI makes coding more accessible. The real value now lies in st...

In this session, Meaghan Choi, Design Lead for Claude Code at Anthropic, demonstrates how to optimize development workflows using Claude AI through advanced features like work trees, custom prototyping skills, and automated pull request management. The video provides a deep dive into the internal practices used at Anthropic to speed up the shipping process while maintaining high design standards. ## Key Takeaways * Use Git work trees to run multiple Claude sessions in parallel without file syst...

This video provides a deep dive into the concept of an AI agent harness, which is a control layer or scaffolding designed to manage complex, long-running tasks for artificial intelligence agents. It explains how these harnesses enable agents to plan, execute, and save progress externally to overcome the limitations of standard context windows and one-shot prompting. By moving away from simple instructions and toward a structured architectural approach, developers can build AI systems that are si...

This video covers the implementation of a multi-provider frontend-mix workflow that leverages the specific strengths of Gemini 3.5 Flash for UI design and Claude Opus 4.8 for logic and reasoning. By routing different stages of a full-stack web application build to different AI models, developers can overcome the limitations of single-model development, such as hallucinations in page copy or poor visual aesthetics in generated interfaces. The process utilizes eight distinct stations and markdown-...

This video covers the transition from static AI harnesses to dynamic workflows in Claude Code, explaining how Anthropic uses multi agent systems to solve complex problems. By generating task specific architectures on the fly, users can bypass traditional limitations of large language models. The content explores the technical foundation of these workflows, the specific architectural patterns that make them effective, and practical ways to implement them for both coding and general knowledge work...