AI/ML Projects

Single-layer transformer in HyperTalk for the classic Macintosh

Running a large language model on a PlayStation 2

Software side of an LLM running inside a DRAM chip via charge-sharing PIM (BitNet b1.58 on DRAM-Bender silicon).

Runtime safety net for LLM agents. Detects token spirals, kills doomed tasks early, tells you exactly why. Rust core, Python SDK. pip install state-harness

Run GLM-4.5-Air (110B) on a 16GB-RAM consumer machine - identify the best memory allocation to overcome standard hardware limitations in Local LLM applications. Placement beats budget. Falsification-Tested laws, probes and recipes for LLMs on commodity hardware

A conv layer that modulates its output using its own kernel weights as a spatial mask

⚡ Real-time AI. Cross-verified. Always current. Costs NOTHING.

Graph-Oriented Generation (GOG)

An experimental fork of Hyprland for compositor-native computer use with visible agent realms.

Tamper-proof memory + cryptographic audit trail for AI agents. HIPAA, SOC2, GDPR compliance built-in. Trust score for every response. Python & TypeScript SDKs. Rust-powered.

I-Driven Topological Optimization of Elastocaloric Metamaterials: Resolving the Fatigue-Porosity Paradox in Solid-State Cooling

Run a 120B-parameter MoE (60 GB) on a 12 GB phone. CPU-only, lossless, on stock llama.cpp

Local LLM inference on Xbox Series S|X (UWP) via ONNX Runtime GenAI.