Links

I am an AI hater. This is considered rude, but I do not care, because I am a hater.

How to select an AI technology and vendor, think about its implications, and apply it to your business.

How do we know if students are learning if ChatGPT is doing the work?

Execute code securely in isolated virtual machines with our high-performance cloud infrastructure.

AI might be a trillion billion balloons filled with confetti.

GitHub CEO warns developers to embrace AI or quit, he said on X, referencing new research. The study reveals how AI is reshaping developer roles and workflows.

Once it’s well integrated into our lives, any new technology can be seen as an exchange. We lose something and get something else in return. When we started using our calculator app, we lost the ability to do basic operations by hand, but we got accurate results quickly. After some time, even making a basic addition without it seems like a struggle. I don’t remember the last time I used a map, other than in school when I was a kid and was learning about them. By the time I got my driver’s license, smartphones were fully out, so Google Maps was my navigator. I lost (or maybe even didn’t develop the capacity to navigate with a map in the first place?), but I got instant directions to any destination in return.

A study into the workflows of experienced developers found that devs who use Cursor for bugfixes are around 19% slower than devs who use no AI tools at all. One possible takeaway is that AI tools can be harder work than we’re led to believe.

Serious learning requires friction, frustration... and other humans

Context Engineering is the new skill in AI. It is about providing the right information and tools, in the right format, at the right time.

The study, from MIT Lab scholars, measured the brain activity of subjects writing SAT essays with and without ChatGPT.

miguelgrinberg.com

An essay about bad AI app design

Fine-tuning LLMs can save tokens, guarantee output formats, & bake in edge-case fixes. Learn when to fine-tune & how to do it effectively for your AI projects.

AI's real threat to education.

Know where AI is a crutch and where it’s an abstraction.

AI is distracting us from creating real value. While we chase speed and automation, meaningful and human-centered work is getting left behind. Is this progress?

A field guide to responsible AI-assisted development

I've been building MVPs and SaaS products for 15 years. Let's work together on your next project.

Developers and marketers are being told to add special files to their sites to help LLMs "understand" their content. But does it do anything?

I enjoy shocking people by telling them I don’t use LLMs.This isn’t true, but it’s morally true for the reference class I’m in (people who wrote a book about...

I'm no longer browsing the web; I'm consuming AI answers instead. I love and adore today's so-called AI answer engines: tools like ChatGPT, Perplexity, Grok, Copilot, and Gemini. I use them at least a dozen times throughout the day, and I'm sure you use them frequently as well. Their convenience is

MCP aims to standardize AI tool integration, potentially simplifying development and enabling more capable AI assistants. Current adoption is limited.

AI agents use models, loops, memory, and tools to automate complex tasks. Learn how they work, their evolution, and their practical uses and limitations.

I recently left my job at Netlify and have been looking at what's next. At Netlify I became very interested in the power of ML, AI and LLMs in particular, and that's the area I've been looking in. But there's a lot of hype and buzzwords around, so I wanted an explainer I can point people to when they ask "but what is all

I started writing a post called "how to write AI apps" but it was over-reach so I scaled it back to this. Who am I to tell you how to write anything? But here's what I'll be applying to my own writing of AI-powered apps, specifically LLM applications. A battle I've already lost is that we shouldn't call LLMs "AI" at all; they are machine learning and not the general intelligence that is implied to the layman by the name. It is an even less helpful name than "serverless", my previous can

There's been a whole lot of discussion recently about the impact of AI on the market for web developers, for programmers in general, and even more generally the entire labor market. I find myself making the same points over and over, and whenever I do that it's time to write a blog post about it, so this is that. Doom and utopia are not our only options There are two extreme takes on the impact of AI on programmer jobs:

Ever wondered how AI agents actually work behind the scenes?

Personal website and blog of Felix Krause

A detailed walkthrough of my current workflow for using LLms to build software, from brainstorming through planning and execution.

Learn effective prompt engineering techniques for AI code generation in WordPress. Discover best practices, examples, and tips for creating clean, organized, and maintainable code

Learn what Large Language Models (LLMs) actually are, how they work, and practical ways to add them to your web projects—no PhD required.

Research recently showed that using AI may impact workers’ long term critical thinking powers. Another alarm bell raises worries that overreliance on AI to help write code will also have a long-term on the workplace.

Understanding LLMs: A Simple Guide to Large Language Models

In this article, I share my personal mental model of how LLMs affect software engineers at different levels, and why this leads to both excitement and scepticism.

It will change it. But how?

AI isn't replacing devs, it's making them more valuable. Let's look at how the job of devs is evolving and how it impacts teams

Secure, compliant AI for mission-critical operations. EXO delivers enterprise-grade AI that runs entirely on your infrastructure.