Freek.dev

You can't out-prompt an attacker — to the model, your system instructions and a malicious support ticket are the same text. So stop defending the prompt and lock down the boundaries you actually control: tools scoped to the authenticated user server-side, middleware that screens and logs, output handled as untrusted input, a human in front of anything irreversible, and a fake-free test that fails CI the moment someone drops the auth scope.

Read more [mujahidabbas.dev]

Matthias writes that AI has shifted more of software development from typing to thinking, reviewing, and iterating. Nice reflection on how agentic coding, parallel worktrees, and voice dictation can slow individual features down while still increasing overall output.

Read more [ma.ttias.be]

Your Agent::fake() tests prove your Laravel AI feature runs — not that its output is any good. This evals a real ticket classifier with the AI SDK: a golden dataset for the fields you can check, an LLM-as-judge for the free text you can't, and a regression gate that catches a bad prompt before your customers do.

Read more [mujahidabbas.dev]

An interesting take on how AI changes the build-versus-buy decision for packages. Shared problems can often be generated, while hard, external, or opinionated problems still benefit from well-maintained packages.

Read more [spatie.be]

Josh Comeau shares a thoughtful take on AI, arguing that deep technical skill becomes more valuable, not less, as these tools improve. His point is that strong developers can use AI to amplify their work, while less experienced builders still struggle without solid architectural judgment.

Read more [www.joshwcomeau.com]

Keith Rabois shares a sharp, opinionated take on how AI is reshaping startups, careers, and product teams. The episode is especially interesting for its thoughts on hiring, the future of product management, and building with more speed and intensity.

Read more [podcasts.apple.com]

In this post, Dries shows how they use Claude Skills to automate repetitive work in client projects, like generating Saloon requests, DTOs, and Livewire pages. It is a practical look at where these workflows save a lot of time, and where careful review still matters.

Read more [spatie.be]

Nick and Dries share how they built Kaartje, a digital postcard wall with a spinning 3D globe that places postcards near the sender's city. It's a fun behind-the-scenes look at the stack, the role AI played during the hackathon, and the performance work needed to render hundreds of postcards smoothly.

Read more [spatie.be]

Sebastian reflects on Robin Sloan's distinction between software's flood fill and the magic circle of the physical world. It's a sharp piece on where AI coding feels limitless, and where paper, printers, post offices, and other real-world constraints still break the illusion of full automation.

Read more [sebastiandedeyne.com]

Sebastian shares a practical three-step workflow for writing feature specs, from gathering notes with tools like Granola to using a thinking model to surface contradictions and scope. He then switches back to hands-on editing to shape the final spec and uses Spiral for a final pass without letting AI take over the writing.

Read more [sebastiandedeyne.com]

Learn how to reuse your Laravel MCP tools in the Laravel AI SDK using a simple proxy approach, helping you avoid code duplication and making it easier to build AI agents integrated into your Laravel applications.

Read more [www.exolnet.com]

A Claude Code skill that helps you design and generate event-sourced domain code for Laravel using spatie/laravel-event-sourcing

Read more [albertoarena.it]

This article frames AI as a tool to support, not replace, developers, emphasizing the importance of staying in control of how and when it’s used. It encourages a thoughtful approach where developers leverage AI for efficiency while maintaining ownership of decisions and outcomes.

Read more [tighten.com]

In this interview, I talk about Laravel, application monitoring, and how AI is changing the way developers work.

Read more

We turned our internal coding guidelines into reusable AI skills, so coding assistants can follow the same conventions their team uses. The package works with Laravel Boost and the broader skills.sh ecosystem, and ships with skills for Laravel PHP, JavaScript, version control, and security.

Read more [spatie.be]

Read more [youtu.be]

Ryan Chandler shares his honest journey from unease to acceptance with AI coding tools. A thoughtful reflection on how your value as a software engineer is not in writing every line, but knowing which lines should exist at all.

Read more [ryangjchandler.co.uk]

A good reminder that trust matters more than ever when every week brings another AI-made product. The post argues that real faces, founder stories, and a visible reputation help both people and LLMs trust what you build.

Read more [marketingfordevelopers.com]

A thorough explainer on how quantization makes LLMs 4x smaller and 2x faster while losing only 5-10% accuracy. Covers floating point precision, compression techniques, and how to measure quality loss, with interactive examples throughout.

Read more [ngrok.com]

Steve Schoger shows how he uses Claude Code to design and build UIs, turning natural language prompts into polished interfaces.

Read more