Browse all articles on AI, technology trends, and personal insights
Every technical team has the same problem: someone draws a great architecture diagram on a whiteboard, takes a photo, and that photo becomes the permanent docum...
I've been running an increasing number of MCP servers and AI tools on my home server, and the configuration sprawl was getting out of hand. Open-Claw-Stack is m...
I've been building MCP servers and tools since the protocol launched, and the collection has grown to over 100 repositories. I maintain a full index at — here'...
I record a lot of voice notes — ideas, meeting recaps, stream-of-consciousness project planning. The problem was always the gap between recording and having som...
I've been using Claude Code daily for about six months now, and somewhere along the way it stopped being just a coding tool and became my primary interface for....
If you've spent any meaningful time working with Claude Code on multi-session projects, you've hit this wall: you're deep into a complex refactor or debugging s...
This document evaluates the current landscape of MCP (Model Context Protocol) aggregation, gateway, and proxy tools as of early 2026. Each tool is assessed agai...
Audio multimodal models can transcribe speech. That much is well established. But what else can they actually infer from a raw audio signal? Can they detect acc...
Living in Israel and working extensively with AI, I have a natural interest in the state of Hebrew language models — and a personal stake in their quality. Hebr...
I keep a living document of the AI tools and infrastructure I use, partly because the landscape changes so fast that I'd lose track of my own setup without one,...
Large language models can be rendered exponentially more powerful by the addition of surprisingly small amounts of contextual data — and I mean genuinely small,...
One of the things I've been exploring extensively is how to make AI assistants actually useful in a personal context. The key insight is that LLMs are dramatica...