Merge Conflict

109: Neural Network C# Predictions for Everyone

August 6th, 2018  |  38 mins 42 secs

ai, android, coreml, ios, keras, machine learning, ml, neural network, plaidml, python, xamarin

It is that time again for more machine learning! This time it is actually something that you can totally build and something that Frank shipped inside of his application to do code prediction using Python, Keras, PlaidML, and CoreML!

Merge Conflict 98: Machine Learning for Space Exploration with Paige Bailey

May 21st, 2018  |  41 mins 49 secs

ai, android, computers, data analytics, ios, machine learning, pluto, programming, python, r, space, space travel, star trek, uwp, west world, xamarin, xamarin.forms

We sit down with the world famous Paige Bailey to discuss the state of machine learning and its impact on space exploration as well as on the coral reef. We of course get into artificial intelligence and how it is impacting every industry out there and we let Paige fill in all the pieces.

Merge Conflict 78: This One is Actually Good

January 1st, 2018  |  51 mins 2 secs

ai, ar, best of, bitrise, c#, continuous integration, new year, top of 2017, visual studio, vr, vsts, xamarin, xamarin live player

Happy 2018! We made it, so let's recap the best in tech, development, life, coffee, and so much more that happened in 2017. We expose our top picks of the year and of course what we are looking forward to in 2018.

Merge Conflict 57: Let's Learn the Machines

August 7th, 2017  |  47 mins 30 secs

ai, android, computers, coreml, ios, ios 11, machine learning, tensorflow, xamarin

Why bother with ARKit when you can learn all about the machines with CoreML! This week we explore all the goodies that Apple has for us in iOS 11's CoreML. We also attempt to demystify exactly what is machine learning and how to get started.

Merge Conflict 45: Build 2017 - No More MSBuild

May 15th, 2017  |  1 hr 1 min

.net core, .net standard, ai, android, build 2017, conference, cosmos db, embeddinator, fluent, fluent design, ios, machine learning, macos, visual studio, xamarin, xamarin live player, xaml standard

The past few days at Microsoft Build 2017 have been filled with wonderful news for .NET and Xamarin developers. We have a full recap of the event, announcements, and a few predictions.

523: UI.md - Opinionated design rules for coding agents

July 13th, 2026  |  46 mins 1 sec

Frank releases UI.md, a practical markdown guide distilled from 25 years of software development that captures essential UI/UX principles to help AI (and developers) build better interfaces. The hosts dive deep into why users expect consistency, how small details create polish, and why understanding your users' mental models beats flashy design every time—with real-world examples from their own apps.

517: Plan First, Think Less: Save Tokens, Improve Code

June 1st, 2026  |  34 mins 49 secs

Episode 517 starts with a light chat about AI avatars and new text‑to‑speech deepfakes before diving into LLM “thinking” modes—what baked‑in planning actually does, why it multiplies token costs, and when it helps or hurts. James and Frank give concrete dev advice: try low‑thinking settings, use big models for creative planning then smaller ones to execute, leverage harnesses/system prompts, and beware quantized local models often do better without thinking.

514: Running Local LLMs in VS Code

May 11th, 2026  |  55 mins 46 secs

In this episode James and Frank dive into running AI coding models locally versus in the cloud—BYOK/Open Router, VS Code’s chat/agent harness, model runners (Olama, vLLM), and the practicality of 27B models on a 3090 using 4‑bit quantization. They share hands-on takeaways—how recent engineering (MT/MTPLX) boosts inference to usable token rates, when auto model selection makes sense, cost and hardware trade‑offs, and why local models can liberate your workflow while still needing smarter, unified tooling.

513: Agents Over Chat: The Future of Developer Workflows

May 4th, 2026  |  57 mins 39 secs

James and Frank explore the future of developer workflows powered by AI agents, revealing how developers are shifting from coders to testers and product strategists. They dive into new research-planning-implementation cycles, GitHub's usage-based pricing changes, and why developers must think strategically about model choices and token costs. Plus, reflections on Apple's leadership transition and the need for bold hardware innovation.

508: Agentic Workflows - Markdown Automation for GitHub Actions

March 30th, 2026  |  40 mins 16 secs

At MVP Summit we dig into Agentic Workflows — write Markdown prompts that drive AI agents to run CI, open PRs, and automate cross‑repo tasks — and MAUI DevFlow, which lets agents interact with native UIs to click, screenshot and validate designs. Listen for practical takeaways on ditching brittle YAML/scripts and automating tedious maintenance and testing, plus the real caveats: security front‑matter, a compile/lock step and token costs.