
521: Polish Matters: UI, Icons, and AI Design Fails
Episode 521 James and Frank obsess over âpolishâ: the tiny design and packaging details that make apps feel finished. They start with impeccable.style, product.md and design.md (and why agents.md and...
29 Jun 48min

520: Inside the New GitHub Copilot App: Sessions, Canvases, Automations
This episode dives into the new GitHub Copilot app â a hub for agent sessions, multiârepo orchestration, PRâfirst workflows, automations and the new canvas metaphor for triage and planning. James and ...
22 Jun 58min

519: WWDC Deep Dive: Appleâs New AI for Developers
James and Frank break down WWDCâs developer-focused newsâfrom Appleâs AI push (local models, a new private cloud for foundation models, and a commandâline API) to Xcodeâs new agent integrations, the d...
15 Jun 52min

518: Windows is Back! New Microsoft AI Coding Models
Microsoft Build 2026 brought a major shift: homegrown AI models designed for efficiency and real-world developer workflows. From the cost-effective MAI Code 1 Flash to sandboxed code execution and Win...
8 Jun 46min

517: Plan First, Think Less: Save Tokens, Improve Code
Episode 517 starts with a light chat about AI avatars and new textâtoâspeech deepfakes before diving into LLM âthinkingâ modesâwhat bakedâin planning actually does, why it multiplies token costs, and ...
1 Jun 34min

516: Evolving Agent Session Management
James and Frank unpack AI-driven development shiftsâagent SDKs, session management, and the rise of agent-first UIs like Googleâs anti-gravity and GitHub Copilotâshowing how VS Codeâs Agents window, w...
25 Mai 42min

515: Mini-LED, IPS, and the Great Monitor Rabbit Hole
James and Frank share thriftâstore monitor triumphs (and a retro Wii audio nightmare) before diving into a noânonsense guide to buying displays: what ports, VESA mounts, and speakers really matter. Th...
18 Mai 44min

514: Running Local LLMs in VS Code
In this episode James and Frank dive into running AI coding models locally versus in the cloudâBYOK/Open Router, VS Codeâs chat/agent harness, model runners (Olama, vLLM), and the practicality of 27B ...
11 Mai 55min



















