Skip to content
Melo Podcasts Home
CategoriesLanguagesFollowing

Episode notes

In this episode, Donn and Kaushik announce that they are steering the podcast back into Android waters. In other words, the Fragmented Podcast is returning to its roots ... we're back to being a 100% Android Development focused show.

Fragmented - AI Developer Podcast

by Kaushik Gopal, Iury Souza · English · Tech & Science

Fragmented is an AI developer podcast for engineers who want to go beyond vibe coding and ship real software. We cover AI-assisted development the way working engineers actually use it: prompting strategies, code review, testing, debugging, workflows, and building production-grade software with…

More from Fragmented - AI Developer Podcast

  1. E247 · 12 Jun 2023 · 1 hr 6 min

    247: The Art of App Modularization with Siggi Jonsson

    In this episode, we talk to, Siggi Jonsson. Siggi helps guide us through the complex and often confusing world of Android app modularization.

  2. E246 · 29 May 2023 · 56 min

    246 - Dependency Injection: Kotlin Inject with Fred Porciúncula

    In this podcast episode, we have the pleasure to host Fred Porciúncula, a Google Developer Expert (GDE) known for his work with Kotlin Inject and his invaluable contributions to the Android development community. Fred offers his expertise on Dependency Injection (DI), Kotlin Multiplatform (KMP), and how they intersect.

  3. E245 · 15 May 2023 · 55 min

    245: Treehouse, Redwood and Zipline with Colin White

    In this episode, Donn and Kaushik talk to an old friend of the show, Colin White, about Treehouse, a combination of the Redwood and Zipline libraries.

  4. E243 · 10 Apr 2023 · 48 min

    243: Mastering the Art of Switching Careers in Tech with Dan Lew

    In this episode, Donn and Kaushik talk to long-time friend Dan Lew about his recent career switch from Android developer to TypeScript/Node.js/Progressive Web App Developer and what he learned.

  5. E242 · 20 Mar 2023 · 40 min

    242 - Kotlin Code Formatting with ktfmt and spotless

    In this episode, Donn and Kaushik talk about one of the age old bike shedding topics - code formatting, and how you can solve it with automation and tools.

  6. E241 · 10 Jan 2023 · 45 min

    241: The Pressure to Ship. Fear, Uncertainty and Doubt

    In this episode, Donn and Kaushik talk about the fear of shipping, some impostor syndrome and how it contributes to uncertainty and doubt in your capabilities as a software developer.

  7. E311 · 6 Sep 2026 · 13 min

    311 - Self learning harnesses are here

    Claude Code and Codex have been the mainstay. OpenCode and Pi showed what open-source harnesses could be. But two new entries just moved the goalposts: DeepSeek's Cordis kernel treats everything — even the agent loop itself — as a hot-swappable plugin, and Prime Agent runs the whole harness inside a live REPL where sub-agents are just function calls. Self-learning harnesses are here, and they're open source.

  8. E310 · 14 Apr 2026 · 1 hr

    310 - Mitchell Hashimoto on Ghostty & His Agentic Coding Workflow

    Mitchell Hashimoto co-founded HashiCorp, built some of the most impressive DevOps tools like Vagrant and Terraform, sold the company to IBM — and then built a terminal. Ghostty is now where a huge chunk of agentic coding actually happens. Mitchell was an AI skeptic. We walk through his six-step adoption framework and the workflows he uses day to day — warm-start research, Hail Mary prompts across twenty GitHub issues, and knowing when to let the agent slam dunk it. Full shownotes at https://fragmentedpodcast.com/episodes/310/

  9. E309 · 1 Apr 2026 · 26 min

    309 - Background Agents

    Andrej Karpathy says the goal is to maximize how long an agent runs without your intervention. But there's a false summit most teams hit first: individual speed goes up while system speed stalls, your laptop roars under four parallel Gradle builds, and review queues back up. Kaushik and Iury trace the full arc — from local multitasking to cloud-hosted async work to fully autonomous agents that fire on repo events and put PRs in your inbox. Full shownotes at https://fragmentedpodcast.com/episodes/309

  10. E308 · 24 Mar 2026 · 25 min

    308 - How Image Diffusion Models Work - the 20 minute explainer

    You already know how LLMs work from our popular 20-minute explainer. Now we take it to images. What does Michelangelo have to do with stable diffusion? More than you'd think. Walk away knowing how image generation actually works — and what it has in common with the text models you already understand. Full shownotes at https://fragmentedpodcast.com/episodes/308/

Every episode of Fragmented - AI Developer Podcast →

Take it with you

The Melo app keeps playing with the screen off, works in the car and on your watch, wakes you to your station, and browses the whole catalogue offline. Free, no ads, no account.

Get it on Google Play