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.
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.
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!
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!
what I'm using:
bsky.app/profile/iury...
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:
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.
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.
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?
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.
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!
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
- Main topic: Fixing Agentic memory - Files all the way down 🐢
- New section: Elsewhere in the Latent Space 🌌
- 🎧 listen to it on the go :)
Check it out!
🔗 This week's issue: newsletter.iurysouza.dev/p/fixing-age...
🔗 Subscribe to get it sooner: newsletter.iurysouza.dev
A good AGENTS[.]md can work as the starting point of an amazing memory system if you incorporate the ideas above, because as it turns out the file system already solved the other half of this.
You might have already realized that if you're using /init to setup your repo you're going to have a really bad time.
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.
🔗 This week's issue: newsletter.iurysouza.dev/p/dead-ides-...
🔗 Subscribe to get it sooner: magic.beehiiv.com/v1/8505b680-...
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-...
🥲
That I also agree. I think this experience is more common on smaller start ups. But it's a huge problem. Legacy code built at an unprecedented speed.
Sec teams must be fuming right now
Im not there yet, but I can see this coming.
