Blomfield loop
Tom Blomfield’s five elements of a self-improving loop: sense, decide, act, verify, and learn.
Loops
Measurement, feedback, evaluation, iteration, and learning what to do next.
Close loops
When the right action is unclear, progress comes from a simple loop: act, observe, learn—and change what you do next.
Building a Google Slides renderer with coding agents
When I read about the Software Factory concept from StrongDM AI, I was intrigued. In part because of the ability to produce an impressively large and complex component. But even more so with how little it might take: could you really do that simply by taking pre-existing specs from the internet and have agents search the program space for
Search in program space
Coding agents run a search in program space. That's the closest analogy I can find for how to use agents productively. If you think of it as an assistant to whom you give tasks, you'll generally be in too tight a loop, giving feedback every few minutes. But the search analogy forces you to consider: 1.
Diverge-converge cycles in LLMs
The Double Diamond is, roughly, a design framework consisting of 4 steps: 1. Diverging on problem (Discover). Explore widely to gather a broad range of insights and challenges related to the problem. 2. Converging on problem (Define). Analyze and synthesize the gathered insights to define a clear and specific problem statement. 3. Diverging on solution (Develop). Brainstorm and generate a
Tesla's data engine: the road to full self-driving
I've driven a Tesla only once but looking at Karpathy's recent presentation at the CVPR conference, soon no human will. I think Tesla's unique data engine is what will get them there. In their self-driving stack, Tesla has always been betting on cameras and radar. This contrasts with Waymo's bet on
If you can measure it, you can improve it
Early this year, I noticed I'd put on some lockdown-weight. I wasn't super worried but wanted to get back to my typical, healthier weight level. My first intuition in this situation was, "let me go on a diet." Diets can work. But they are expensive: you spend willpower every day on avoiding the
To kill a mock-up, first
I ran my first design sprint last week. According [https://www.gv.com/sprint/] to the creators: > The sprint is a five-day process for answering critical business questions through design, prototyping, and testing ideas with customers. The starting point of a sprint could be a problem like “website visitors don’t understand our product.” Monday is spent mapping
Your AI team needs DataOps
A startup’s AI work often starts from a developer hacking algorithms on the side. When a generalist engineer with no data science background works on prediction problems, they often don’t use a dataset at all, or at best a small one. For example, in the early days of Veriff, a front-end developer tried to build a feature
Data loops are the bottleneck in applied AI
You can quickly iterate code, but not data. This is one of the major bottlenecks in companies trying to automate human activities, and solving it generally would change the way every machine learning team works. To understand how easy things could be, consider a simple web application. To make a small change to the site – e.g. changing the way