Paulo Kopzinski

Brazilian, programmer and traveler, crafting code and exploring the world.

[Neuralink @neuralink]

The dura is the brain's armor: a membrane so tough that a surgeon normally cuts through it with a scalpel. For the first time in our clinical trials, we inserted the electrode threads of our implant straight through the dura and into the cortex, keeping the dura intact.

Here's how we did it 🧵

[Claude @claudeai]

Introducing Claude Sonnet 5, our most agentic Sonnet yet.

It makes plans, uses tools like browsers and terminals, and runs autonomously at a level that just a few months ago required larger and more expensive models.

[Paulo Kopzinski @kopzinski]

Must confess, I'm testing @grok Grok Build and it's kinda smooth, nothing to complain til now (better than copilot and pretty much like claude code)

[Uncle Bob Martin @unclebobmartin]

if anything you want your agents to do is deterministic, such as managing a queue, or sorting a list, create a script for the agent to use. Agent's don't do deterministic things well. It's our job to force determinism upon them.

[Nate Berkopec @nateberkopec]

AI can be a (financial) bubble and LLMs can still be a very useful technology. Hold two thoughts in your head at once.

[Paulo Kopzinski @kopzinski]

That was my first thought when using LLM for coding

[Uncle Bob Martin @unclebobmartin]

one of the great advantages of working with agents is that they actually understand git.

[Uncle Bob Martin @unclebobmartin]

I start with very informal specifications written by hand. I have an agent convert these into harder specifications that are subdivided into tasks. I review these.

Then I feed those tasks into the specifier agent, which converts each task to Gherkin, prunes the Gherkin, and then hands it off to the coder agent. I spot check the Gherkin.

The coder agent writes acceptance tests directly from the Gherkin. Then writes unit tests. Then writes code. When all those tests pass, the coder agents hands off to the refactorer agent.

The refactorer agent reduces crap to 6 or below, and reduces any duplication. Then it write property tests and gets them to pass. Then it hands off to the architect agent.

The architect agent runs language mutation and covers any uncovered sections, and kills all survivors. Then it runs Gherkin mutation and kills any of those survivors. Then it runs the entire test suite, and when it passes it hands the result off to the specifier, coder, and refactorer.

I spot check the code.

This is an exercise of transformations from the informal to the formal through managed stages, with human interaction decreasing with each stage.

Raw computer power is the limiting factor. Those mutation tests are CPU intensive.

[TechFX @thetechfx_]

Quais os modelos de contratação mais comuns para vagas internacionais?

E quais os primeiros passos e cuidados após receber o "sim" da vaga?

[Paulo Kopzinski @kopzinski]

Codex doesn't seem to "sign" the commit as co-author with you as Claude does.

[DHH @dhh]

Omarchy 4 is going all-in on Quickshell. I mean, just look at these gorgeous background and theme selectors!

[Uncle Bob Martin @unclebobmartin]

Authoring code by hand HAS GONE AWAY.

Engineering module structure and architecture has not.

[TANSTACK @tan_stack]

SECURITY ADVISORY — TanStack npm packages
A supply-chain compromise affecting 42 @tanstack/* packages (84 versions total) was published to npm earlier today at approximately 19:20 and 19:26 UTC. Two malicious versions per package.
Status: ACTIVE — packages are deprecated, npm security engaged, publish path being shut down.
Severity: HIGH — payload exfiltrates AWS, GCP, Kubernetes, and Vault credentials, GitHub tokens, .npmrc contents, and SSH keys.
If you installed any @tanstack/* package between 19:20 and 19:30 UTC today, treat the host as potentially compromised:
• Rotate cloud, GitHub, and SSH credentials immediately
• Audit cloud audit logs for the last several hours
• Pin to a prior known-good version and reinstall from a clean lockfile
Detection — the malicious manifest contains:
"optionalDependencies": {
"@tanstack/setup": "github:tanstack/router#79ac49ee..."
}
Any version with this entry is compromised. The payload is delivered via a git-resolved optionalDependency whose prepare script runs router_init.js (~2.3 MB, smuggled into each tarball at the package root).
Unpublish is blocked by npm policy for most affected packages due to existing third-party dependents. All 84 versions are being deprecated with a SECURITY warning, and npm security has been engaged to pull tarballs at the registry level.
Full technical breakdown, complete package and version list, and rolling status updates:
https://t.co/Zy8qG7PA9f
Credit to the security researcher for responsible disclosure.

[Elon Musk @elonmusk]

❤️❤️ Happy Mother’s Day ❤️❤️

Appreciation to mothers everywhere who brought us all into the world and nurtured their beloved children 🥰

[Paulo Kopzinski @kopzinski]

Paradox of the day: I type more on my keyboard now because of LLMs than before they even existed

[Paulo Kopzinski @kopzinski]

Thought LLMs would steal my job… but they just became a new way of programming.
Contexts, agents, prompts, MCP — now we all speak one language.
Share knowledge properly and we’ll accelerate progress like crazy.

[Paulo Kopzinski @kopzinski]

Be ready to live in buildings made by LLMs

[Claude @claudeai]

With the Autodesk Fusion connector, designers and engineers can create and modify 3D models through conversation.

[Uncle Bob Martin @unclebobmartin]

I’ve been harping on the disciplines and tools for using AI lately. I find them to be a very effective approach. But I don’t want to leave you with the impression that a few simple disciplines and tools is sufficient.

As the AI’s build software, you — the software engineer — need to have a good mental model of what the AI is doing. You need to apply engineering insight to correct it when it takes a path you don’t like. You have to be an active manager in the design and architecture of the system. You have to be able to “see within“ without resorting to exhaustive code reviews. You have to form suspicions about what the AI is doing, and you have to probe and experiment to verify your suspicions.

[ClaudeDevs @ClaudeDevs]

Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found.

All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.

[SpaceX @SpaceX]

SpaceXAI and @cursor_ai are now working closely together to create the world’s best coding and knowledge work AI.

The combination of Cursor’s leading product and distribution to expert software engineers with SpaceX’s million H100 equivalent Colossus training supercomputer will allow us to build the world’s most useful models.

Cursor has also given SpaceX the right to acquire Cursor later this year for $60 billion or pay $10 billion for our work together.

[Elon Musk @elonmusk]

You can access 𝕏 APi via @OpenClaw.

We’re trying to make it affordable without giving away the shop.

Hopefully, this can be useful & fun 💫