Newsletter
Thoughts on AI, development, and technology. Published on Substack.
Running an Uncensored Qwen 3.8 27B Cybersecurity Lab with Hermes
A practical local setup for authorized red-team and blue-team research on Windows, Linux, and macOS...
Build an AI Assistant That Can Help You With ADHD
A local setup for sorting out a busy head, getting started on things, and remembering where you left off. Using Hermes and Qwen 3.8, with instructions for Linux, Windows, and Mac....
I Ran Qwen 3.8 27B on a Single RTX 5090. Here's What Actually Worked
262K context, an uncensored GGUF, native MTP, and a final result of ~133 tokens/sec on one consumer GPU....
Building a Completely Local AI Security Lab with llama.cpp, OpenWebUI, Splunk, and MCP
Running a Large Language Model on Consumer Hardware Without Sending Your Data Anywhere...
Qwen3.6-35B-A3B-MTP at 70 tok/s on an RTX 3070
I’ve been running Qwen3.6-35B-A3B-MTP on my RTX 3070 (8GB VRAM) for a while now and previously documented getting ~55 tok/s....
Multi-Token Prediction MTP in llama.cpp How It Works and How to Use It
PR #22673 just landed in upstream llama.cpp, and it is a big deal....
The Architecture Breakthrough Nobody in Local LLM is Talking About
If you’ve been following the local LLM space this year, you’ve probably been tracking parameter counts, quantization methods, and hardware requirements like a stock trader watching candlesticks....
A 760M-Parameter Model That Beats GPT-5-High on Math
Let’s talk about a paper that quietly dropped on arXiv this week and absolutely deserves more attention than it’s getting....
Living with ADHD as an adult in 2026
I hate the fact that I can sit down and wrestle with complex problems for hours....
Google Silently Deploys a 4GB Local LLM to Every Chrome User
Google has quietly installed a 4GB local LLM into Chrome, and billions of users have no idea it is there....
Running Qwen3.6-35B-A3B-MTP at 55 tok/s on an 8GB GPU
A Practical Guide...
This Idea Might Change How AI Actually Thinks
and it quietly reveals something deeper about knowledge, logic, and how natural thinking really works...
Why are we looking for a 'flat' signal in song production?
A small piece on why we use monitors, EQ's and other things in order to get a flat frequency response....
How to tune your subwoofer and monitors correctly
The correct way to set the cutoffs on your studio gear....