Ramblings of Jakob Serlier
Extending Karpathy's llm-wiki with event-driven document management: a pragmatic setup for ingesting personal documents into an LLM-friendly wiki, driven by filesystem events and a small Rust daemon called eventic.
A short note on iterating an LLM through a dozen drafts of a semi-formal paper, in service of a tabletop card-game disagreement that turned out to be more interesting than expected.
On AI-generated pull requests, cognitive load, and the slow death of review quality.
A transient billing failure caused irreversible loss of a grandfathered Spotify Duo plan that is no longer available in the UAE. No retry, no warning, no recovery path.
Giving a self-hosted OpenClaw agent read/write access to one Obsidian folder via Docker volume mounts, rclone bisync, and GPT OCR for handwritten notes.
A practical approach to safely running AI coding agents with strong isolation using cloud VMs, Tailscale, and simple notification patterns.
Atlas can browse and extract real numbers, but it gives up on simple repetition of this task.
Showcasing telemetry redaction work with Microsoft Presidio: official samples, client-side masking demos, and automated OTLP interception patterns.
Comparing manual and automated approaches to PII masking in observability pipelines using Microsoft Presidio, with practical insights from healthcare workloads.
Building a minimal focus timer with GitHub Spark in under 20 minutes - why personalized tools are becoming trivial to create.
A practical approach to measuring AI Assistant impact on development work using git trailers and automated hooks.
Building a SaaS platform with dynamic OpenTelemetry routing to customer-specific Azure Application Insights instances.
Showcase: Azure AI Hybrid Search unexpected results gotcha
Showcase: Azure AI Hybrid Search unexpected results gotcha
Inject hidden prompt in LLMs using Base64 encoding.
What does a statement like “AI will take my job” look like in practice?
Showcase: gpt-4 CLI with persistence in 10 lines of code.
Showcase: Voice record daily thoughts and notes and redact using GPT4 using Apple Shortcuts natively.
An exploration of the RAG pattern in Large Language Models, highlighting the importance of evaluating their performance using question-answer pairs. The article also delves into the challenges and benefits of using both golden and synthetic (silver) datasets for development and assessment
Using LLMs for auto-generating unit tests aids rapid development in building Python libraries, but while beneficial, it's no substitute for deliberate test-writing and might create a false safety net
Using GZIP compression and the k-Nearest Neighbors algorithm, we explore an innovative approach to classifying the MNIST dataset with about 78% accuracy
We have recently engaged in an architecture design & upskilling session with an enterprise customer for building a solution using an LLM as part of their *reasoning engine*. Their aim is to utilize this to assist engineers in navigating complex technical documentation. This is a collection of some of the learnings
This post discusses the concept of self-governing AI, its prerequisites and the prospects of realizing it in the current state of AI technology.
I had been avoiding properly setting up remote networking to my homeserver. Tailscale solved my problem in under 5 minutes.