@adlrocha Beyond The Code

For six days, the most popular model on OpenRouter was completely anonymous.

Last week I closed the Kimi K3 post promising you that I’d do the same exercise of explaining the improvements of the newly released Qwen3.8 and GLM5.3 models in plain English.

Back to our regular schedule, welcome back to a new season of “Beyond the Code”.

As promised a few weeks ago, I’ll try to force myself to have a break from writing through August in order to build up my backlog so I can ensure more high quality content again starting on September.

Back in January I wrote about my “Spec-Test-Lint” workflow and ended it with a small promise: I wanted to start tinkering with remote development environments.

I gave a talk earlier this year at CONVEX, in Madrid, in an actual cinema.

A quick confession before we start.

For six months I’ve been trying to hedge my (and my family’s) access to intelligence.

A few weeks ago I wrote about the shift from GPU-poor to token-poor.

A reader messaged me last week with a question about a topic that has been in my backlog for a few months now, AI and the physical world.

Last week I ended this newsletter questioning if the people inside the labs actually see the same end-of-cycle signals the rest of us are reading from the outside, or are they rushing their IPOs because they can see something coming that the market hasn’t…

I don’t know about you, but I feel like the mood around AI is shifting slightly.

Last week I wrote about the shift from writing code to running the kitchen.

After the detour we made the last few weeks exploring the state of the hardware and software stack of local AI inference, I want to come back to one of the topics I promised to address in my posts about agent engineering.

Last week I wrote about the hardware side of running AI locally, why memory bandwidth matters more than raw compute, which machines are worth building, and where the market is heading.

A few weeks ago, GitHub announced that Copilot is moving to usage-based billing.

I wanted to close this series of posts from the past few weeks on agent engineering with the top of mind problem of everyone that starts building an agent to deploy it in production, but that I don’t see nearly enough people talking about openly.

Last week’s post on the Claude Code leak surfaced something I keep coming back to: the most interesting engineering in a production AI agent isn’t the model, it’s everything around it.

The dust has finally settled.

A few weeks ago I wrote about how I thought intelligence is becoming a commodity.