Notes from the workshop.
Product updates, engineering notes, and thinking on privacy-first AI tooling.
Run Mistral locally: Europe's open family, and the license lines you can't cross
One command runs the best open code model in the world. Shipping what it writes breaks the license. Europe's open family, mapped.
Run DeepSeek locally: the reasoning model in a laptop-sized package
It wiped $600B off Nvidia in a day and you still can't run it. But DeepSeek bottled that reasoning into a 9 GB download. Here's which one your laptop handles.
Run Qwen locally: one open family for chat, code, vision, and audio
Most labs hand you one good model. Alibaba's Qwen hands you a toolbox (chat, code, vision, audio, search), and almost all of it is a free download.
Meta Llama, explained: which model is for what, and how to run it
It started the open-weights era and still sets the baseline everyone benchmarks against. Now its creator is hinting it might stop. The map, before that happens.
What is an embedding? How AI turns meaning into numbers
Spotify hands you thirty unheard songs and a third are keepers. The trick: it turns meaning into coordinates, then measures the distance.
What is prompt injection? The flaw every AI agent ships with
One email, no click, and Copilot mailed a stranger your files. The bug behind it can't be patched: the AI can't tell orders from text.
What is MCP? The standard that lets AI actually do things
A year ago your AI invented the numbers. Now it opens the file and reads them. The thing that changed wasn't a smarter model. It was a plug.
Production got free. Taste got expensive.
By April 2026, 44% of the music uploaded to Deezer every day was machine-made. When everyone can make anything, making it stops being the job.
What is RAG? How AI looks things up instead of guessing
Your chatbot just quoted a refund policy that doesn’t exist. RAG is the one-line fix: make it read the document before it answers.
The AI coding tool landscape in 2026: Cursor, Claude Code, Antigravity, and the rest
Cursor vs. Claude Code is the wrong fight: they’re different species. The five-category map, and the one thing most reviews miss.
Google Gemma, explained: which model is for what
Type “gemma” into your runtime and you get a wall of models: a phone-sized one, a workstation one, and odd cousins. Here’s which one you actually want.
The best open AI models you can run locally right now
The model that nearly tied the closed coding leaders is a free download, if you pick the right one for your RAM and dodge the license traps.
Siri just proved the point: the most personal AI runs on your device
Apple rebuilt Siri and rented a $1B Gemini brain, yet kept the part that reads your life on your device. The line it drew is the lesson.
Why does AI make things up? Hallucination, explained
Seventeen court rulings in one day flagged invented citations. AI isn’t lying to you: it’s guessing, exactly as it was taught.
What is an AI agent? A model in a loop, explained
The AI that fixed 2% of real bugs in 2023 fixes 95% today. The difference isn’t a smarter model: it’s a loop. Here’s how it works.