The Model Changed. My Skill Didn't. The Score Still Dropped.
My rule for evaluating an agent skill is deliberately asymmetric: Test the agent on the weakest model you intend to support. Choose the judg...
Oct 7, 2026
7 min
Strata Squeezes a 125-Billion-Parameter AI Onto a Gaming PC. Here's How.
Strata runs a 125-billion-parameter AI model on a normal Windows or Linux PC with a 12 GB+ NVIDIA or AMD card. I read through the repo and d...
Oct 5, 2026
9 min
Gemini 4 Argon: Google's new flagship is here, and almost nobody can use it yet
Gemini 4 Argon is Google’s new frontier model, leading on knowledge work, long-context reasoning and several benchmarks. But coding is mixed...
Oct 1, 2026
7 min
What to do when users use your AI for sex stuff
What happened I have a little Werewolf text game with LLMs. With a caveat - there is a role-play. Each game has a theme, a lore, a topic - a...
Sep 30, 2026
9 min
Jev, Explained: The AI That Refuses to Write a Word
Jev is a “System One Model” that returns typed, calibrated probabilities for predefined question types in a single forward pass, enabling fa...
Sep 24, 2026
4 min
Image Generation with Ollama is back with Japanese, Korean and Chinese Languages 🇯🇵 Support!
An international collaborative work 🎌 Introduction At the start of the year, I...
Sep 11, 2026
8 min
Prompting Is Not Magic. It Is Control.
Most prompt books optimize for better answers. I wanted prompts that fail visibly. Most prompt...
Sep 6, 2026
8 min
What is Text Watermarking?
Implementing a didactical ‘water marking’ sample application (for self learning and...
Sep 6, 2026
6 min
Google Slides AI is laughably bad
I was making a slide in Google Slides recently when a small button appeared at the bottom: Beautify the slide.
Sep 3, 2026
3 min