SYSTEMATIC TRADING / LOCAL AI / PUBLIC NOTEBOOK
I build and test technical systems across systematic trading, local AI infrastructure, and agent-assisted development. This site records the experiments, guides, benchmarks, and decisions behind the work.
Local AI
Hardware guides, tooling notes, benchmarks, and practical local-first AI infrastructure.
A comparison of WRX80, TRX40, and AMD EPYC motherboards for multi-GPU local AI builds, with UK marketplace prices, PCIe lanes, memory bandwidth, Threadripper Pro CCD layouts, remote management, and the risks of importing used server hardware.
Selected research
Notes on market behaviour, execution, risk, and systematic edge.
After the expansion-filter research, I tried to attack the drawdown problem more directly by detecting consolidation and filtering it out. The visual idea still makes sense, but the first binary versions were too thin to separate the bad loss clusters cleanly.
Selected projects
Tools for testing ideas faster, keeping evidence clean, and making research repeatable.
active
Python / MQL5 / MT5
A research framework for hypothesis intake, AI-assisted MQL5 implementation, parallel MT5 backtesting, evidence review, and experiment lineage.
Built around structured hypotheses, reproducible test runs, versioned evidence, and reviewable agent-assisted implementation.
Recent writing
A long-form record of questions, observations, experiments, and changing beliefs.
No essays published yet.