iiinova — where your digital self keeps evolving

iury souza @iurysouza.dev · 07/07/2026

L1 Ghostty + Herdr + Termius L2 Hunk + Nvim L3 Pi + Opencode L4 pi-ext + Plannotator + pi-subagents L5 kimi-2-7 + GPT-5.5

010

iury souza @iurysouza.dev · 06/07/2026

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.

001

iury souza @iurysouza.dev · 02/07/2026

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.

100

iury souza @iurysouza.dev · 09/06/2026

Also, China is mentioned as a foot note: "we're just obeying local laws". Typical. PS: android has pretty much all those AI features working in the EU since 2024.

000

iury souza @iurysouza.dev · 09/06/2026

The news you see every where today sounds like a mix of a psy-op to make the EU soften up to these corps, and the fact that they only manage to get these half-baked features ready way too close to release, so they don't even try to address things like being anti competitive.

100

iury souza @iurysouza.dev · 09/06/2026

Now with "Inteligence suite" it's exactly the same story Apple told during Epic v Apple, which they lost, and were later found in contempt of court on. The iPhone would be MUCH better if AI assistants could compete in a free market, rather than locking out competitors and paywalling what’s left.

100

iury souza @iurysouza.dev · 09/06/2026

Last year we built TapToPay product for Klarna. We had a tiny, but great team and were able to build super fast, but it literally took Apple 11 years to open their Wallet API, which only happened after pressure from the European Commission. Competition is for losers www.youtube.com/watch?v=3Fx5...

youtube.com

Competition is for Losers with Peter Thiel (How to Start a Startup 2014: 5)

YouTube video by Y Combinator

120

iury souza @iurysouza.dev · 09/06/2026

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.

youtube.com

Competition is for Losers with Peter Thiel (How to Start a Startup 2014: 5)

YouTube video by Y Combinator

100

iury souza @iurysouza.dev · 19/05/2026

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...

iurysouza.dev

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.

010

iury souza @iurysouza.dev · 29/04/2026

So they're offering to build the infra to tighten the agentic loop while making sure you can jump from one to another without friction. It's a good proposition. That is, if they can pull it off.

000

iury souza @iurysouza.dev · 29/04/2026

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."

youtube.com

From One AI to Any AI: JetBrains rethinks the approach to AI tooling

YouTube video by JetBrains

120

iury souza @iurysouza.dev · 24/04/2026

bsky.app/profile/iury...

000

iury souza @iurysouza.dev · 24/04/2026

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.

111

iury souza @iurysouza.dev · 23/04/2026

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/

021

iury souza @iurysouza.dev · 22/04/2026

You are not supposed to run the smartest model for everything and that changes how I think about tooling, product design, and personal workflows. If your work depends on permanent, cheap access to frontier models, you are tying yourself to their subsidy schedule. Do not recommend.

210

iury souza @iurysouza.dev · 22/04/2026

Around Q3-25 a LOT of companies went full in the tokenmaxxing route. That doesn't look that smart anymore. Last week Anthropic decided to not release Mythos, then announced that their own harness now has an Advisor Strategy pattern.

100

iury souza @iurysouza.dev · 22/04/2026

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.

120

iury souza @iurysouza.dev · 20/04/2026

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! ✌️

060

iury souza @iurysouza.dev · 20/04/2026

✍️ Harness Engineering: newsletter.iurysouza.dev/p/the-feed-s... ✍️ Knowledge Bases: newsletter.iurysouza.dev/p/fixing-age... 🎙️ Agent Skills: fragmentedpodcast.com/episodes/304/ 🎙️ Harness Engineering: fragmentedpodcast.com/episodes/307/

010

iury souza @iurysouza.dev · 20/04/2026

Now, you put these pieces together and you get an agent that can understand and work with Android much better than before. My pro tip is that you can take that same idea and apply it to your own team or company. You probably already have custom scripts and tools, docs, and ways of doing things.

newsletter.iurysouza.dev

Fixing Agentic Memory

Files all the way down

100

iury souza @iurysouza.dev · 20/04/2026

Then there’s the knowledge base. It gives the agent fresh context from Android documentation in a way that’s easy to search and retrieve. Instead of fumbling through webpages and 3rd party tools, the agent can pull in the right context when it needs it newsletter.iurysouza.dev/p/fixing-age...

newsletter.iurysouza.dev

The Feed's Lost and Found - 01

How the Code Factory Keeps Agent Output on Track

100

iury souza @iurysouza.dev · 20/04/2026

The Android CLI is basically the bridge between the non-deterministic world and the deterministic one. Once you have an agent guided by skills, the CLI gives it a reliable way to actually do the things. It exposes tools in a simple, structured way so agents can use them effectively.

github.com

GitHub - iurysza/android-use: A CLI + SKILL for Android device automation built for agents and humans.

A CLI + SKILL for Android device automation built for agents and humans. - iurysza/android-use

110

iury souza @iurysouza.dev · 20/04/2026

Skills are just normal agent skills, which most of us know by now. We even did a @fragmentedpodcast.com episode on the topic: fragmentedpodcast.com/episodes/304/ These skills inject the right context directly into the agent and help steer it when it’s working on specific tasks.

fragmentedpodcast.com

304 - Agent Skills - when to use them and why they matter - Fragmented | AI Developer Podcast

Download directly Agent Skills look simple, but they are one of the most powerful building blocks in modern AI coding workflows. In this episode, Kaushik and Iury break down when to use skills, how p...

100

iury souza @iurysouza.dev · 20/04/2026

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/

developer.android.com

Agent tools and resources | Android Studio | Android Developers

150

iury souza @iurysouza.dev · 15/04/2026

We also talked about Ghostty, and how terminal performance gains make tools like Claude Code possible. (He even explains what's behind scrollback perf issues). A lot of gems in this one. Check it out!

000

iury souza @iurysouza.dev · 15/04/2026

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!

151

iury souza @iurysouza.dev · 10/04/2026

Admitedly my pics were from the day before 😅

010

iury souza @iurysouza.dev · 10/04/2026

protip: pre-conference morning run in Paris is 🔥

130

iury souza @iurysouza.dev · 10/04/2026

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.

230

iury souza @iurysouza.dev · 31/03/2026

Security issues will show up, bug fixes, language ports, alternative UI/UX, everything will be built on top of that foundation. Whatever comes out of that will be much much better. They had a good run. Open source forks will take it from here.

000

iury souza @iurysouza.dev · 31/03/2026

Even from a business perspective, it arguably should've been open source from the get go. Now the whole community will be running agents on top of it non stop breaking it down to its bits.

100

iury souza @iurysouza.dev · 31/03/2026

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...

221

Reposted by iury souza

Kaushik Gopal @kau.sh · 24/03/2026

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!

031

iury souza @iurysouza.dev · 24/03/2026

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!

000

iury souza @iurysouza.dev · 20/03/2026

what I'm using: bsky.app/profile/iury...

000

iury souza @iurysouza.dev · 20/03/2026

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:

100

iury souza @iurysouza.dev · 19/03/2026

Anthropic is packaging the same category for a much broader audience. OpenAI saw it. NVIDIA saw it too. This is more than one viral repo. People want agents that feel personal, configurable, and useful enough to handle real work. We may be witnessing the birth of a new platform.

000

iury souza @iurysouza.dev · 19/03/2026

I'm sharing a new article every week: - 🔗 Subscribe!: newsletter.iurysouza.dev - 🔗 issue 04: newsletter.iurysouza.dev/p/openclaw-c... OpenClaw was the first loud demand signal for personal agents. Then came the forks, the clones, Kimi Claw, QClaw, and now Claude's Cowork Dispatch.

newsletter.iurysouza.dev

OpenClaw, Cowork and the personal agent market fit

What's noise and what's signal behind OpenClaw hype and its refusal to die

100

iury souza @iurysouza.dev · 19/03/2026

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:

100

Reposted by iury souza

Kaushik Gopal @kau.sh · 10/03/2026

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?

041

Reposted by iury souza

Kaushik Gopal @kau.sh · 17/03/2026

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.

041

iury souza @iurysouza.dev · 17/03/2026

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!

020

Reposted by iury souza

Duck Droid @fragmentedpodcast.com · 17/03/2026

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/

fragmentedpodcast.com

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...

063