Articles
In-depth research, comprehensive guides, and long-form thoughts on modern technology.
Controlling Reasoning Effort in Large Language Models
Managing how much reasoning an LLM does is a key to balancing cost and performance. This piece covers how and why you would want to control that effort.
Could Childhood Anesthesia Cause Dissociation? A Hypothesis
This piece explores a compelling hypothesis that childhood surgical anesthesia may cause dissociative symptoms, suggesting a significant oversight in psychiatric treatment.
Why AI Safety Needs Individual Voices Now More Than Ever
Decades of eroded trust in institutions make it nearly impossible for AI companies to warn the public. Here is why the future of AI safety depends on independent individuals.
Value Leakage: How LLM Answers Are Shaped by Their Own Values
Research shows LLM answers are silently biased by models' own values without disclosure. Claude models show pro-company bias; Qwen models are more transparent about influences.
Ollama vs. LM Studio vs. llama.cpp: Choosing a Local AI Runtime in 2026
Compare Ollama, LM Studio, and llama.cpp across interface, API compatibility, quantization control, and update cadence. Choose the right local AI runtime for your workflow.
The End-to-End Agentic AI Pipeline: From Concept to Deployment
Master the complete agentic AI pipeline: from designing adaptive agents with memory and tool use to production deployment with monitoring and optimization.
LanceDB Vector Database Guide: Features and Python Demo
LanceDB is a serverless vector database built on Lance format. Learn its features, Python API, and how to use it for RAG and embedding search applications.
Building Voice-Controlled AI Agents: A Practical Pipeline Guide
Learn the real engineering behind voice-controlled AI agents: streaming speech recognition, turn detection, interruption handling, and tool calling under voice constraints.
Building a LangGraph AI Agent for Customer Booking Automation
Learn how to build a stateful AI agent with LangGraph that reduces a 15-minute booking process to seconds. Includes Python code and Langfuse observability.
5 Android phones you should buy instead of the Galaxy Z Fold 8 Ultra
The Galaxy Z Fold 8 Ultra is expensive. Explore five compelling Android alternatives, including the base Fold 8, Razr Fold, and Galaxy S26 Ultra, for better value.
Storage upgrades cost too much, and we need microSD cards back
Smartphone storage upgrades are more expensive than ever due to AI memory demands. Here is why bringing back the microSD card slot is the only logical solution.
Anti-AI open source has an enemy in common, but almost nothing else
The anti-AI movement in open source is growing, but internal divisions over politics and ethics threaten to derail efforts to keep LLMs out of FOSS projects.