How to Get Blazingly Fast Text Search in Your CLI That Doesn't Suck »

Exact keyword matching is fast in the CLI. When text is spelled differently, or you cannot remember how it was written, you need to upgrade your search tools. This article explains how.

I have a lot of information sitting in text files on disk, including Markdown notes, text files, source code, PDFs, Word documents, notebooks, and various other formats spread across local and external drives. Finding a file by name is easy. Finding a file because you remember …

The Death of the Billable Hour : The Emergence of Software Factories and Outcome-Based Pricing »

Why AI is pushing software consulting from billing hours to pricing outcomes, and what you'll need to deliver them.

Most software consultancies bill, one way or another, for the work of building software. AI now does a growing share of that building, 1, which raises an interesting question for anyone who charges by the hour: if a tool absorbs much of the construction, what is the client still …

Interview Series - From Classical Guitar to Ruby on Rails »

A professional musician turned software engineer - on career pivots, side projects, and building with AI.

Preamble This conversation tracks an engineer who started professional software development in October 2022 - two months before ChatGPT shipped. He arrived from outside the field with a music bachelor’s and a few years as a working classical guitarist. Four years on, he …

MemPalace - A Short Case Study in AI Systems Engineering »

Illustration: Milla Jovovich engineering in a sea of documents A short case study in AI systems engineering: Hollywood actress Milla Jovovich released an AI memory system with 12k+ stars on GitHub. MemPalace - A short case study in AI engineering and marketing. Yes, that Milla …

Moore's Law for AI? »

From Single-Core Limits to Multi-Agent Systems Moore’s Law [1] fueled decades of computing progress by predicting the doubling of transistor density approximately every two years. For a long time, this translated into rapid gains in CPU speed-until thermal limits and the …

The Four Paradigms of Prompting »

Introduction Large language models (LLMs) map sequences of text to other sequences of text. Given an input string, an LLM predicts the most probable continuation based on the statistical patterns it has learned during its training process. What makes LLMs remarkable is not merely …

uv - An Extremely Fast Python Package and Project Manager, Written in Rust »

There exist a broad selection of package managers that manage virtual environments and packages for us. Some of the most popular ones are conda, pip and virtualenv or virtualenvwrapper. They can almost all do the same things: Install packages Resolve dependencies Managing package …

How to Choose Tech for Production: The Default Heuristic »

Introduction During my time as a lead data engineer to build a predictive maintenance platform I came across the concept of the default heuristic. One of my tasks was to identify platform components that would allow us to scale storage and retrieval of time series sensory data to …

The Difference Between a Base LLM and an Instruction-Tuned LLM »

Introduction Large language models (LLMs) can behave very differently depending on how they were trained. BaseLLMs are trained purely on next-token prediction over a large corpus of text. Instruction-tuned LLMs, by contrast, are further trained to follow prompts in a more helpful …

Interview Series - Working with an SRE »

Preamble In this insightful interview, Paul Bütow, a Principal Site Reliability Engineer at Mimecast, shares over a decade of experience in the field. Paul highlights the role of an Embedded SRE, emphasizing the importance of automation, observability, and effective incident …