iiinova — where your digital self keeps evolving

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 · 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

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 · 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

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

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

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

iury souza @iurysouza.dev · 12/03/2026

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

100

iury souza @iurysouza.dev · 09/03/2026

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.

010

iury souza @iurysouza.dev · 04/03/2026

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-...

130

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

Im not there yet, but I can see this coming.

310

iury souza @iurysouza.dev · 02/03/2026

Yeah, so the thing is the model is completely different. That one is the dense version of the 3.5:35b. I shared more details on linkedin. (should fit better than plain text here) 👇 www.linkedin.com/feed/update/...

010

iury souza @iurysouza.dev · 02/03/2026

That's what I tried before. It's 4x slower than the alternative.

110

iury souza @iurysouza.dev · 02/03/2026

Jumped from 20 TPS to 80 TPS ⚡ on my M4 Pro. The trick is that this version uses a MoE architecture with 3 billion active parameters. That makes it way faster. I was running the base model via GGUF (ollama), and now running on MLX (vlm - because this is a vision model too).

221

iury souza @iurysouza.dev · 01/03/2026

We're speeding through the synchronous agent flow. Lots of development in that area too.

110

iury souza @iurysouza.dev · 01/03/2026

The IDE as we used to know is dying and no one bats an eye

100

iury souza @iurysouza.dev · 27/02/2026

Friendly reminder that Sonnet 3.5 (on paper it's sonnet 4.5) runs on your Mac for free now. t.co/ZmqCZRRkTC

240

iury souza @iurysouza.dev · 26/02/2026

Function calling everywhere! (kinda looks like MCP though) with AppFunctions If this picks up, the way we use phones will drastically change (and a lot of apps might stop making sense)

110

iury souza @iurysouza.dev · 26/02/2026

Super happy to be back in Paris for @androidmakers.bsky.social! This time I'll be spreading the word on Edge-AI! (Or how to make your phone go brrr!) Now, srsly. Edge AI is heating up (no pun intended) and there's a LOT going on. Watch this space! C'est parti 🇫🇷! tinyurl.com/droidcon-fr-...

031

iury souza @iurysouza.dev · 25/02/2026

Check from the Google office for the Cloud & Al Train-the-Trainer Roadshow in Berlin! Getting knowledge on the more advanced tools and tech for building agents straight from the source. Let's go!

170

iury souza @iurysouza.dev · 24/02/2026

"It's only called legit distillation if it comes from the silicon valley region of California"

111

iury souza @iurysouza.dev · 24/02/2026

Big rewrites are coming to a codebase near you. Expect them.

000

iury souza @iurysouza.dev · 18/02/2026

New buzz word: Ever heard of Harness Engineering? At this point, names don't matter that much*, but it's clear the field is changing at neck break speed and the more I read and talk to "practitioners" the more it is clear to me that these will become established practices: 🧵

120

iury souza @iurysouza.dev · 17/02/2026

🎙️Check out the new @fragmentedpodcast.com episode on subagents! They can be a huge unlock once you understand how it all works and you can get real benefits without having to a swarm them. @kau.sh and I built an RTS mental model for how they work (yes, we did that). Check it out!

062

iury souza @iurysouza.dev · 16/02/2026

I still use bsky, but most of the hot content on AI comes from other apps, newsletters, blogs, and random links. Keeping up is really hard. So I built a personal feed and turned into a public page: iurysouza.dev/feed I'll be also sending a free weekly digest with context if you signup ✌️

130

iury souza @iurysouza.dev · 12/02/2026

Oh, in that case I totally see that. Pretty crazy to have such fast adoption and product fragmentation at the same time, right? reminded me of when I was testing the whole skills.sh thing. 39 agents lol

110

iury souza @iurysouza.dev · 12/02/2026

More about that on this week's pod, 25min episodes no BS: 🔗 fragmentedpodcast.com/episodes/304/ Bonus points: To get started, you just get the agent to do the lengthy discovery process, and then turn that convo into a skill. And then just tune it as you go. Let it do the writing.

030

iury souza @iurysouza.dev · 06/02/2026

As of today, the Agent counter at 39 > Are you not entertained?

020

iury souza @iurysouza.dev · 06/02/2026

It's super interesting to see great engineers going all in on their AI-coding learning journey. This is from Mitchell Hashimoto (from HashiCorp/Terraform, Ghostty): mitchellh.com/writing/my-a... Some things resonate with my experience and some are completely new to me. Great read.

110

iury souza @iurysouza.dev · 04/02/2026

Just got my second android smart watch ever. 150 EUR off 👌 The last one I had was the og Huawei watch 1.( which still works 7 years later BTW) Let's see if this one holds that long :D

031

iury souza @iurysouza.dev · 03/02/2026

Thinking traces can be so useful! I keep them always on.

000

iury souza @iurysouza.dev · 03/02/2026

On the topic of building/managing context, this is the main idea. Build useful context, save it somewhere, feed it to the llm when it makes sense. Then you may build commands/skills to generate them and load them back when needed.

010

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

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!🎙️

083

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

Im leaning towards this opinion for some time. Occam's razor, man... www.youtube.com/watch?v=AcwK...

210

iury souza @iurysouza.dev · 01/02/2026

Paste the repo link to your agent and ask it to install the skill. Restart and ask away

020

iury souza @iurysouza.dev · 01/02/2026

Ok, I've been nerd sniped into building this. First step: android-use CLI+SKILL github.com/iurysza/andr...

350