Research & infrastructure
Responsible AI, from the inside out.
Hard-won lessons at the intersection of AI security, adversarial evaluation, and agentic systems — written by a practitioner for practitioners.
Latest
- Qwen3.8 on One Card ·Part 1
Fitting Qwen3.8-27B on One RTX 3090: The Memory Math Is Wrong in Both Directions
A 27B model with 262K context on a single 24 GB card. The obvious memory arithmetic overestimates the cost by 4x, then underestimates the ceiling. What actually fits, how fast it runs, and where the efficiency knee sits.
- Evaluation Methodology ·Part 1
Behavioral and Mechanistic: AI Evaluation's Missing Loop
Behavioral evals and mechanistic interpretability are usually framed as two camps. They are not. They are two halves of a method neuropsychology has been refining for decades.
- Home AI Lab ·Part 2
Building a Home AI Inference Node, Part 2: Adding llama.cpp and Going From Chat Server to Research Workstation
Part 1 made the node stable. Part 2 makes it useful for research: adding llama.cpp as a second runtime, GGUF model control, and the OpenAI-compatible API that ties it together.
- Home AI Lab ·Part 1
Building a Home AI Inference Node, Part 1: WSL, Ollama, and the Windows Problems Nobody Mentions
What I actually ran into turning a Windows desktop with an RTX 3060 Ti into a persistent local AI server accessible from my MacBook over LAN, and why the hardest problems had nothing to do with AI.
Stay in the loop
New posts on AI security, responsible AI evaluation, and agentic systems — no noise, no cadence pressure. When there's something worth reading, it lands in your inbox.