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-...

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

I started writing a newsletter to keep up with what's going on on AI coding developments. This is the last week's issue recap 🧵. A new one comes out tomorrow. Subscribe! iurysouza.dev/newsletter/t...

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).

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

If you're using an AGENTS.md generated with /init you're gonna have a bad time.

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

www.anthropic.com/news/stateme... $ claude --dangerously-skip-constitutional-rights

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)

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-...

First edition of The Feed's Lost and Found is live! I break down harness engineering, code factory loops, and how teams are keeping agent output on track. Fresh out of the press. Get it while it's hot 🔥 iurysouza.beehiiv.com/p/the-feed-s...

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!

@kau.sh and I bring you some agentic coding goodies on the pod's newsletter. Check it out!

This was fun for both of us! We share some of how the fragmented 🌭 is made + Tips from @iurysouza.dev and me, and a crazy way we used AI to solve very real audio problems 😉.

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

100% this Custom task trackers or planners, systems of records, memory. Also skills specific to each codebases, closing the agentic loop (running tests, linter, check logs, databases, ui components). All of that makes the flow much more reliable and are a must now. mgratzer.com/posts/forgin...

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: 🧵

new episode is out! spot the easter 🥚? recent models have shown massive improvement owing to clever use of "modes" and subagent dispatch. it really clicked for me after chatting with @iurysouza.dev listen to improve your fundamentals! (not just tactics).

🎙️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!

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 ✌️

👌

If you haven't tried yet, Codex 5.3 xhigh is a really interesting model. (Make sure you select xhigh!) It's really thorough. Takes way longer to answer, but can be really worth it.

CLIs 🤝 Agent Skills It's not because your agent can complete a task with dozens of tool calls and 50k tokens that it should. So what do you do? You can build a script that does the same in a deterministic way in a single 1 milisecond call instead of 4minutes back and forth. 🧵

Skills are an amazing agent tool, but I can't wrap my ahead around people using package managers for installing them. It's like npm supply-chain on roids: - agents can read files - agents can run commands - agents can exfiltrate data - users install them without reading any of the code/text.

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!🎙️

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

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.

Highly recommend this @gergely.pragmaticengineer.com interview with @booch.com "Software engineering has always been a tale of rising complexity." The abstraction changes, but engineering stays. Industry isn't collapsing, but the hubris won't help either. Be pragmatic!

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

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

Some notes on what's working for me in agentic-coding atm. - close the loop (build/lint/test/run/inspect ui/logs/debug) - cap multitasking - rly - Focus on guarding boundaries (I/O + validation + tests) - Build and use opt-in context - subagents: few roles/min tools iurysouza.dev/my-agentic-c...

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!🎙️

If you can't explain it to a 6-year-old... Neither of us is 6, but I definitely came out of this one with a much better understanding of how Large Language Models work 🤘 @iurysouza.dev and I try to explain the most important concept of our time in 20 minutes.

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

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

It seems a lot of people are now converging on the idea that CLIs are a great fit for coding agents. Both for automating things for us humans and for building agent skills. These are some ideas and guidelines on how to build a good one. Great resource. clig.dev

The future is software writing its own software. Which is why I'm so in love with Pi: a coding agent that can extend itself :) lucumr.pocoo.org/2026/1/31/pi/

Great article from @mitsuhiko.at's about how Pi is the engine behind @steipete.me's OpenClaw. Such a cool concept and philosophy for this kind of tool. I bet you can learn a lot about this "agentic paradigm" building around this. lucumr.pocoo.org/2026/1/31/pi/

Question for our mobile devs out there: Do you have mcps or skills recommendations for tooling that closes the agentic Loop? I just heard about xcodebuildmcp and I wonder if there's something for Android github.com/cameroncooke...

protip: Stop using sonet-4.5 for everything agentic. Latest gen of open source models have gotten reaaly good at agentic stuff. This is just a basic task comparison, but here GLM-4.7 is both faster, spends less tokens and is about 10x cheaper. model: z.ai/blog/glm-4.7

I built something reaaaly similar for myself last november. Pretty cool to see! iurysouza.dev/shadow-claude/

IMO this is impacting everything, not only OSS. There's just too much code being written. How can reviewers meaningfully keep up? Who's going to review all that? The old PR review model is being stretched to its limit.

oh well

On the same note: github.com/steipete If you check @steipete.me current projects you'll notice that half of Clawdbot's features come from other tools he's been building. COMPOSABILITY!

Nothing makes this argument better that @simonwillison.net 's tools repo: tools.simonwillison.net That's exactly it!

We're in warpspeed. God help us all hahah

I'm open to work! People know me for my skills in Android, Kotlin, Compose, Gradle, Android Automotive, or for my hunger in eating issues for breakfast. You might also know me from my talks at @droidcon.bsky.social! I'm proud to have worked with the best at @snappmobile.bsky.social. New adventures!

just beware with nerd sniping 💀

Likely the most fun and compelling use case to me. With the this opportunity cost drop, we can now take more ownership of our tools and maximize our ability to get things done. Tasks that require many steps can be reduced to a single command. Thats the real unlock. iurysouza.dev/craftsmanshi...