How I AI, hosted by Claire Vo, interviews and case-studies from people using AI. Released as Audio and Video
Episodes
13 Jul 2026
"Running AI locally offers cost savings, unlimited usage, and privacy, with high-performance hardware enabling automation for tasks like security scans and code reviews, while balancing cloud integration and future AI-driven workflows."
Open episode
8 Jul 2026
"Harnesses are structured frameworks that enhance AI agent effectiveness by integrating tailored tools, workflows, and constraints for specific tasks like debugging or support, improving efficiency and control over outcomes."
Open episode
6 Jul 2026
AI automates small business tasks like inventory tracking and order management via tools such as "magic glasses," explores personal AI use cases (e.g., Codex for hobby tasks), delves into autonomous agent orchestration with cloud-based workflows and GitHub, addresses challenges like scalability and model behavior, and reflects on AIs potential to bridge physical-digital systems, reduce manual effort, and enhance productivity while highlighting underutilized automation opportunities.
Open episode
30 Jun 2026
Anthropic's Claude Sonnet 5 offers Opus-level performance at reduced costs with enhanced agentic capabilities, while a new benchmarking framework evaluates its competitive edge against models like Gemini 3 Pro and GPT 5.5, highlighting the need for standardized, human-informed evaluations to balance objective metrics and subjective quality.
Open episode
29 Jun 2026
A streamlined AI agent development approach using minimal infrastructure, agile methods, cross-functional collaboration, and rapid iteration enabled a five-person team to build a functional product in 10 weeks by prioritizing speed, adaptability, and automation over traditional planning and complex tools.
Open episode
24 Jun 2026
GLM 5.2, an open-weight model from Z.ai, offers a 1 million-token context window, strong performance on coding and reasoning tasks, cost-effectiveness, and local deployment flexibility, though it lacks image support and struggles with modern frontend frameworks.
Open episode
22 Jun 2026
Recommended: AI finds bugs
Firefox employs AI agents as "coding archaeologists" to detect and address security vulnerabilities in its massive codebase, leveraging models like Mythos and custom validation tools to identify and systematically fix nearly 500 bugs, while balancing automation with human oversight and open-source collaboration to enhance scalability and security.
Open episode
17 Jun 2026
Prompts and loops in AI automation are highlighted for their role in enabling structured task execution through clear automation design, sandboxed workflows, plugins, and subagents, with applications in software engineering and integration with tools like GitHub and Slack.
Open episode
15 Jun 2026
AI integration in software engineering enables agents to handle complex tasks through benchmarking and optimization, shifts engineers toward higher-level work, and addresses challenges like reliability, data parsing, and balancing automation with human expertise while emphasizing outcome-focused systems over procedural methods.
Open episode
9 Jun 2026
Anthropic's Claude Fable Five excels in long-term technical tasks with strong coding, vision, and async workflow capabilities but faces high token costs, design limitations, and restricted use in cybersecurity/biology, making it suitable for precise, extended projects rather than creative or agile workflows.
Open episode