Every few months, we hear the same prediction:
“Software engineers will be obsolete in 6 to 12 months.”

This time, the warning came with a bold experiment.

The Cursor team — backed by billions in venture capital — decided to prove that AI agents could replace engineers. Instead of just talking about it, they launched a real test:
Hundreds of AI agents working nonstop for a week to build a web browser from scratch.

Building a browser is one of the hardest engineering challenges in modern software. Even Microsoft struggled with it for years. So if AI could pull this off, it would be a huge milestone.

But what happened next tells a very different story. Read More

I have written eight of these guides since ChatGPT came out, but this version represents a very large break with the past, because what it means to “use AI” has changed dramatically. Until a few months ago, for the vast majority of people, “using AI” meant talking to a chatbot in a back-and-forth conversation. But over the past few months, it has become practical to use AI as an agent: you can assign them to a task and they do them, using tools as appropriate. Because of this change, you have to consider three things when deciding what AI to use: Models, Apps, and Harnesses. Models are the underlying AI brains; Apps are the products you actually use to talk to a model, and Harnesses are what let the power of AI models do real work. Until recently, you didn’t have to know this. 

It means that the question “which AI should I use?” has gotten harder to answer, because the answer now depends on what you’re trying to do with it. So let me walk through the landscape. — Read More

Have you ever spent hours debugging code that Claude had written 30 minutes before?

Exact same model, same chat, and same prompting. For some reason, Claude starts ignoring previous decisions you made together or ignores mentioned markdown files, only to then present blatantly incorrect suggestions.

You aren’t at fault here. Instead, you’re experiencing context rot. — Read More.

Forget the hype. This is what really happens when you build AI systems in Python and C++, and why the “one language” debate misses the point.

On the surface, it sounds like a simple “this or that” question. But if you’ve actually built stuff — broken stuff, fixed stuff at midnight, and argued with teammates over which language is better — you know it’s not that simple. The short version? You probably need both. The long version? Well, that’s what this post is about. — Read More

#devops

Mitchell Hashimoto, a HashiCorp co-founder, shares his approach to AI adoption.

My experience adopting any meaningful tool is that I’ve necessarily gone through three phases: (1) a period of inefficiency (2) a period of adequacy, then finally (3) a period of workflow and life-altering discovery.

In most cases, I have to force myself through phase 1 and 2 because I usually have a workflow I’m already happy and comfortable with. Adopting a tool feels like work, and I do not want to put in the effort, but I usually do in an effort to be a well-rounded person of my craft.

This is my journey of how I found value in AI tooling and what I’m trying next with it. In an ocean of overly dramatic, hyped takes, I hope this represents a more nuanced, measured approach to my views on AI and how they’ve changed over time. — Read More

At Pinterest, ads are more than just advertisements; they are a vital part of the content ecosystem, designed to inspire users and connect them with products and ideas they love. Our goal is to surface the right ads at the right time, ensuring they seamlessly integrate into a user’s shopping journey and provide genuine value. To achieve this, understanding user behavior is paramount.

Delivering highly relevant ads in a dynamic environment like Pinterest presents unique challenges. Users’ interests and shopping intents evolve rapidly, making it crucial for our ad systems to adapt and anticipate their needs. Traditional ad targeting methods often rely on broad demographic data or static interest categories, which can fall short in capturing the nuanced and evolving nature of user behavior. — Read More

… Some time ago I wrote about “the 70% problem” – where AI coding took you to 70% completion, then leave the final 30% last mile for humans. That framing may now be evolving. The percentage may shift to 80% or higher for certain kinds of projects, but the nature of the problem changed more dramatically than the numbers suggest.

Armin Ronacher’s poll of 5,000 developers compliments this story: 44% now write less than 10% of their code manually. Another 26% are in the 10-50% range. We’ve crossed a threshold. But here’s what the triumphalist narrative misses: the problems didn’t disappear, they shifted. And some got worse. — Read More

Every decade brings new promises: this time, we’ll finally make software development simple enough that we won’t need so many developers. From COBOL to AI, the pattern repeats. Business leaders grow frustrated with slow delivery and high costs. Developers feel misunderstood and undervalued. Understanding why this cycle persists for fifty years reveals what both sides need to know about the nature of software work. — Read More

#devops

For a long time, we were all hand-wringing over the shortage of software developers. School districts rolled out coding curriculums. Colleges debuted software “labs”. “Bootcamps” became a $700m industry.

Today, we have the opposite problem. Thousands of trained, entry-level engineers that no one wants to hire. — Read More

Lowering the barrier to creation has always been a net positive. WordPress turned anyone into a publisher. YouTube turned anyone into a broadcaster. Shopify turned anyone into an e-commerce operator. AI-assisted coding is doing the same for product building.

Let a thousand flowers bloom. I’m all in!

The problem: AI is very good at helping you build something. It’s not very good at helping you build something well.

The difference matters. — Read More