L1 Ghostty + Herdr + Termius L2 Hunk + Nvim L3 Pi + Opencode L4 pi-ext + Plannotator + pi-subagents L5 kimi-2-7 + GPT-5.5
iury souza
@iurysouza.dev
Platform Eng @ Sumup • GoogleDevExpert • 🎙️ Co-host @fragmentedpodcast.com • Agentic Coding • terminal maximalist - 🔺MG em Berlim - iurysouza.dev - linktr.ee/iurysza
Feels like ages ago. You'd be hard pressed to find anyone who disagrees with this trajectory nowadays, but back then it felt almost like a taboo in some circles.
iury souza@iurysouza.dev · 8mo agoI’ve avoided this topic because of the noise and heated debates, but I think we recently crossed a line. The polarization is still there but it doesn't change the outcome anymore: this isn't a fad. It's the new baseline. iurysouza.dev/agentic-codi...
Markdown -> HTML -> Gen-UI Introducing Visual Artifact Renderer: github.com/iurysza/visu... (i probably need a better name) If you end up trying it, let me know what you think.
I have as much content for Euro bureaucrats as the next person, but dont fall for this story as " The mean EU" blocking "poor little Apple" from releasing nice features to their users.
Competition is for Losers with Peter Thiel (How to Start a Startup 2014: 5)
YouTube video by Y Combinator
youtube.com
developers.googleblog.com/an-important... RIP Gemink CLI. I like the vision. Hope it works :)
An important update: Transitioning Gemini CLI to Antigravity CLI- Google Developers Blog
Announcement for the sunsetting of Gemini CLI in favor of Antigravity CLI, a more robust, agent-first platform designed to handle the multi-agent complexities of 2026.
developers.googleblog.com
The better agents get, the easier it is to outsource the part you probably shouldn't outsource: figuring out what to build. Plan Mode should only used after extracting the intent behind the task. Ive added a few tools to my workflow for achieving that. More on that: iurysouza.dev/newsletter/w...
Why Plan Mode is making things worse
No good plans can be created before you have a shared understanding of the underlying intent. Here's how to fix that.
iurysouza.dev
www.youtube.com/watch?v=J8fH... I actually liked Jetbrain's positioning here. "Bring your own agent (ACP compatible) and we'll make sure it is capabilities are augmented by the tools we build."
From One AI to Any AI: JetBrains rethinks the approach to AI tooling
YouTube video by JetBrains
youtube.com
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.
Mitchell Hashimoto shares how he views Ghostty as a platform for the next generation of TUI applications. This is just a clip from ep 310 of the @fragmentedpodcast.com. Full episode: fragmentedpodcast.com/episodes/310/
SOTA is becoming a luxury tier. I think that is the cleanest way to read what has been happening lately. State-of-the-art models were always too expensive to serve at scale and now that bill is finally due.
Still buzzing from my time at AndroidMakers 🇫🇷 by droidCon! It was awesome to share about edge-AI, to catch up and listen to exchange ideas with people building great products! Thanks to @gregfawson.bsky.social and all the staff for making this happen! Till next time! ✌️
The 🤖 Android team just released three things that are a great example of what your team or company can build too: - Android Skills - Android CLI - Android Knowledge Base developer.android.com/tools/agents/
Agent tools and resources | Android Studio | Android Developers
developer.android.com
This week @kau.sh and I had the pleasure to chat with Mitchell Hashimoto on the pod🎙️! Refreshing to hear someone of his caliber bring such a grounded perspective to agentic coding. We're super proud of this one!
Duck Droid@fragmentedpodcast.com · 4mo ago🎙️ Our first guest in the AI series is the legend @mitchellh.com 🎙️ We covered a lot of ground and learned a tonne from him: 👻 Ghostty's internals and why tmux & certain shells strip its best features. His path from AI skeptic to cautious optimist.
I’m at Android Makers 🇫🇷 this afternoon talking about “Practical On-Device AI on Android.” Excited to share about features unlocked about this new capability, reliability, hybrid approaches, models, and more. If you’re around, come join! I’d love to meet people working on similar problems.
Claude Code’s source code leaked last night. Given the speed and sheer volume of forks and spin-offs already popping up, agentic harnesses are about to surge really hard. It’s crazy out there and I actually love to see it 😈 github.com/chatgptproje...
this one was fun to make. @iurysouza.dev and I took a crack at explaining how image models (stable diff.) work in ~20 minutes. building an intuition around AI is starting to matter a whole lot and that starts by understanding the mechanics. hope you get as much out of it as we did making it!
Duck Droid@fragmentedpodcast.com · 4mo agoOur 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
If you want to get some intuition behind how some of the image models out there work, this episode is for you! @kau.sh and I had a go to try and break it down in a short episode. No need for a masters in deep learning to understand some of the clever tricks behind image generation. Check it out!
Kaushik Gopal@kau.sh · 4mo agothis one was fun to make. @iurysouza.dev and I took a crack at explaining how image models (stable diff.) work in ~20 minutes. building an intuition around AI is starting to matter a whole lot and that starts by understanding the mechanics. hope you get as much out of it as we did making it!
If you're unsure what model your machine can handle, you can check axjns.dev llmfit. It's a TUI that profiles your hardware and scores models to tell you exactly what fits in your RAM/VRAM. This is it running on my mac:
Issue 04: Openclaw, Cowork and the personal agent market fit Openclaw hype refuses to die and while the project had obvious safety issues from day one people still wanted it anyway. Anthropic realized that and just released Cowork's Dispatch feature. I write more about this on the newsletter btw:
love the analogy that Iury gave - think of your AGENTS[.]md like the constitution of your codebase! we also go into an important paper that tries to answer the question that we've all had at some point - are these AGENTS files we're all meticulously creating, even worth it?
Duck Droid@fragmentedpodcast.com · 5mo agoAre 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
This is the real work that teams need to put in, to get the best results from their AI coding agents. listen to our latest episode on Harness Engineering.
Duck Droid@fragmentedpodcast.com · 5mo agoOpenAI 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/
Platform engineering for agents! If you know plat-eng, you get how tooling helps teams move faster while keeping code standards. Now Harness engineering bridges that concept, turning a repository into an environment purposebuilt for agentic coding. Think we're finally getting out of the weeds!
Duck Droid@fragmentedpodcast.com · 5mo agoOpenAI 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/
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/
307 - Harness Engineering - the hard part of AI coding - Fragmented | AI Developer Podcast
The hard part of AI coding isn’t generating code — it’s controlling quality, safety, and drift. Drawing from OpenAI’s Codex case study, Stripe’s Minions project, and real-world experience, Kaushik and...
fragmentedpodcast.com
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
A System of Record, maps of content and grep. That's pretty much all you need to have HUGE gains in agentic memory. Agents are pretty good at walking text when the path is marked well. This is the main topic in this week's issue: newsletter.iurysouza.dev
Fixing #AISlop with a #SKILL.md in #geminicli Well, at least, removing as much sloppiness as possible from AI generated text! And making it more human-readable ☺️ Inspired by the awesome tropes.fyi Explanations and skill: glaforge.dev/posts/2026/0...
This is why your AI generated text sounds like a lobotomized corpo bot. Either due to time pressure or just basic lack of taste™, a lot of people using AI just don't realize that. I rly hope we can collectively fix this asap.
As a developer, keeping up with AI is super hard and that's precisely why I started this newsletter. These are the best stories I read in the past week. My (human) thoughts on what I think matters and why. No AI slop. 🎧 listen to it on the go :) 🔗 newsletter.iurysouza.dev/p/dead-ides-...
