Writings

Built a minimalist team trackerNote

2025-10-14

We were talking yesterday between colleagues and I on motivating each other to keep moving. Made track.jakobs.dev to easily keep each other…

Building personalized focus apps in minutes.Post

2025-10-12

Coding with AI agents creates this peculiar problem: you get these short 10-30 second waits while the model thinks, and it's just long…

Created Focus!Note

2025-10-12

Create the focus tool! focus.jakobs.dev

Tracking AI Assistant Contributions Using Git Trailers and Git HooksPost

2025-07-28

It can be challenging to pinpoint the 'concrete' impact AI assistants have on daily development work. For example, during a workshop I was…

Dynamically Routing Traces to Customer-Specific App InsightsPost

2025-07-07

When building a SaaS offering publishing platform that helps customers publish azure marketplace offers, we faced an interesting…

Creation of KoppelWerkNote

2025-02-07

Today, we started KoppelWerk.

Learnings from ingesting millions of technical pages for RAG on Azure.Post

2024-05-06

Learnings from ingesting millions of technical pages for RAG on Azure. Context overview This document outlines insights of an engagement…

Showcase: Azure AI Hybrid Search unexpected results gotchaPost

2024-04-30

Showcase: Azure AI Hybrid Search unexpected results gotcha This document describes a gotcha in Azure AI Search hybrid queries where…

Encoding hidden prompt in LLMs as potential attack vector.Post

2024-01-15

The recent publication on LLM "sleeper agents" prompted me to re-explore influencing LLMs to pursue alternative objectives. In this case…

What does a statement like “AI will take my job” look like in practice?Post

2023-11-21

What does a statement like “AI will take my job” look like in practice? On two different occasions and coincidentally, I have been…

GPT-4 CLI with persistence in 10 lines of code.Post

2023-11-03

A short one: I needed a GPT-4 CLI interface (that's a RAS Syndrome), but most options seemed quite cluttered, and I like code-golf. Here an…

Voice record daily thoughts, redact with GPT4, and save to Apple Notes using Shortcuts.Post

2023-11-02

The why Recording my daily thoughts and notes is a challenge I return to every few months, and so far, I hadn't figured out a system which…

Evaluating RAG/LLMs in highly technical settings using synthetic QA generationPost

2023-10-26

In short: The RAG pattern for LLMs can be evaluated using QA pairs. Creating a "golden" dataset is expensive, but an auto-generated "silver…

On automating unit tests with LLMs.Post

2023-10-19

Dear colleagues, I have a confession to make: I have been delegating some of my unit tests to my Jr. engineer, Gary-Pete Truman. First off…

78% MNIST accuracy using GZIP in under 10 lines of code.Post

2023-09-20

GZIP Addendum after hitting the HN frontpage: MNIST is a straightforward dataset, and higher accuracies are possible with various methods…

From Concept to practice: Learnings from LLMs for Enterprise Production – Part 0Post

2023-08-18

Disclaimer: I am an employee at Microsoft ISE. However, the views and opinions are of my own. We have recently engaged in an architecture…

One approach to achieving self-governing AI todayPost

2023-02-06

Note: I will not discuss the alignment issue or responsible AI / ethics. A self-governing AI is capable of solving any challenge in the…

What defines great software: solving my problem in under 5 minutes with TailscalePost

2022-05-04

TL;DR: I had been avoiding properly setting up remote networking to my homeserver. Tailscale solved my problem in under 5 minutes. Today, at…