Duck Droid

bsky.app/profile/iury...

Ever wondered why they still can't fix Claude Code flickers? Spoiler: It's not because of TS/JS or react! Mitchell Hashimoto (Ghostty's author) explains in this short clip the reason behind that and how Ghostty could address the root cause, enabling even more demanding TUI applications.

Karpathy's goal for agents: maximize how long they run without intervention. While individual speed goes up, "system" speed doesn't (the false summit ⛰️). Listen to Ep 309 — Background Agents: fragmentedpodcast.com/episodes/309 where we resolve this tension.

Our LLM explainer (ep 303) got pretty popular, so we thought we'll follow up with the natural progression - How do image models work (in 20 minutes). also... what does Michalangelo have to do with stable diffusion models? 🤔 Listen to ep 308 to find out fragmentedpodcast.com/episodes/308

OpenAI spent 20% of every week cleaning up AI slop from their own coding agents. So they built a "harness" shaping the agent's environment so the slop never ships in the first place. @kau.sh & @iurysouza.dev talk about "Harness Engineering" in the latest ep. fragmentedpodcast.com/episodes/307/

Are AGENTS[.]md files even useful? There’s finally a paper asking the obvious question. @kau.sh and @iurysouza.dev get into the paper, the sync problem, and the small amount of discipline required to stop your agent setup from turning into a mess. 🎧 fragmentedpodcast.com/episodes/306

Master subagents and your AI coding sessions stay sharp for hours with clean results. Under the hood though? they're just a tool call. One model prompting another in a scoped context. 💡 New ep breaks down what they are, when to spawn them, and when not to. fragmentedpodcast.com/episodes/305/

Everyone's talking about OpenClaw (Clawdbot) right now. But what makes it so extensible? Agent Skills! modular SKILL mds that teach an agent how to do anything. We do a deep dive in episode 304 on when to use them, how they work, and how not to get pwned. 🎧 fragmentedpodcast.com/episodes/304

Its really useful to get some intuition of how LLMs work so that you can get the most out of them. This was tricky to do, but I guess @kau.sh and I did a good job of breaking down how LLMs work on a 20min, audio-only episode. I always learn smth when I revisit this topic. Check it out!🎙️

Ever get asked "how do LLMs work?" and freeze? 🎧 Listen to Ep 303 and fix that 🎧 fragmentedpodcast.com/episodes/303/ We walk through tokenization, embeddings, and inference: the full pipeline in 20(ish) minutes. Enough to hold your own at the next dinner party.

What are MCPs? are they worth the token cost? 🎧 Listen to Ep 302 and find out! 🎧 fragmentedpodcast.com/episodes/302/ We break down what an MCP actually is, how it differs from just using CLIs, the tradeoffs you should know about, and when MCPs actually make sense for your workflow.

🎧 Episode 301 is out - AI coding ladder 🎧 Most developers say AI coding like it's one thing but it's not. Listen to @kau.sh & @iurysouza.dev talk about the different AI coding paradigms. Listen to this episode and find out where you are on the ladder! fragmentedpodcast.com/episodes/301/

Been a Fragmented listener since before I got my first dev job. Surreal to now be joining @kau.sh as co-host for this new Al focused season! Looking forward to getting into the ins and outs of Al coding! What actually works, what doesn't, and how to think about all of it. Let's do this! 🎙️🤘

🎧 Episode 300 is now out! 🎧 From Vibe Coding → Software Engineering Announcing our biggest pivot and our new cohost @iurysouza.dev 🤭 You have to listen to the episode just to hear Iury's take on AI. 🤭 fragmentedpodcast.com/episodes/300

Big changes coming to @fragmentedpodcast.com New direction. New cohost. New episode numbering. Full story drops in the episode coming out on Monday. But if you want a sneak peek (updates in our email newsletter). buttondown.com/fragmentedcast

excited to end the @fragmentedpodcast.com hiatus with a new season: a developer's crash course on #AI #programming just enough theory but more "how do I actually build with this?" i'll start with fluency, then dive deep. help me shape the first few episodes:

Why I still podcast for @fragmentedpodcast.com ❤️ kau.sh/blog/fragmen...

thanks for sharing our starter template episode ! 🙏

I had the honor of chatting with @kau.sh and sharing some predictions, hot takes, mental models and how I'm thinking about where to spend my time amid all the chaos. We anchor the conversation on the recent interview that I published in my newsletter with 10 other Android experts. #AndroidDev

Ever wonder if your #AndroidDev skills will still be relevant in 3 years? 🤔 @vinaygaba.bsky.social did the digging for you! We got the juicy predictions and some sage wisdom 🧘. New ep out: 🎧 Future of AndroidDev (in an AI world) with Vinay Gaba 🎧 fragmentedpodcast.com/episodes/257

New episode it out! 🎧 Rapid prototyping with Kotlin tech 🎧 What are the tools in your utility belt? fragmentedpodcast.com/episodes/256/

Thanks for sharing episode 255 on DOP (Data Oriented Programming) @androidweekly.bsky.social in your latest letter 🙌 I really think this paradigm pushes us to model systems better and is a powerful tool for improving software engineering craftsmanship. fragmentedpodcast.com/episodes/255/

🔈 Our first episode of this year and season is out — Data Oriented Programming 🎧  First #AndroidDev #podcast episode for 2025. We're resumed our new season, so episodes coming your way every week! fragmentedpodcast.com/episodes/255/

Excited to announce the next season of @fragmentedpodcast.com. Starting next week, I should drop a fresh episode every Tuesday for the next 5 weeks. The switch lets me prep better (and take a breather 😅). Want to catch up on prev episodes? check our 📬 - buttondown.com/fragmentedca...

Kotlin Weekly #439 has just been published! - mailchi.mp/kotlinweekly...

Latest Android Weekly Issue 655 is out! androidweekly.net/issues/issue... #AndroidDev #Kotlin

Final phase of @fragmentedpodcast.com's reboot is nearly done! 📬 Newsletter drops early Jan with some fun exclusive meta talk on how some of the episodes came about. Subscribe for free → buttondown.com/fragmentedca...

8× increase in speed and 5× reduction in memory usage with Dan Rusu's Immutable Arrays in Kotlin 🤯  Tune into our grand finale #AndroidDev #podcast episode for 2024.  https://fragmented-android-developer-podcast-479ffc54.simplecast.com/episodes/254

"Everyone need a template" and I cannot agree more with the @fragmentedpodcast.com Building in KMP (currently using CMP) is an absolute pain in the ass regarding dependencies. I cannot see myself do this again and again. #AndroidDev #iosdev

Thanks as always for sharing our content and other incredibly useful android reads 🙌

🎧 new episode #253 is out! logcat - a new look at logging with @p-y.wtf from Square. Listen here: fragmentedpodcast.com/episodes/253/ #AndroidDev #Podcast

go.bsky.app/BWjNgtr Thank you @p-y.wtf for the wonderful idea (still building the list)

🤖 hello world 🤖