(Click to skip) →
Articles
Lisper: AI Speech Therapy for Lisps
A quick writeup on Lisper, my Gemma 4 Good Hackathon submission for low-anxiety lisp speech practice.
BS-Bench: What a Bluffing Card Game Revealed About LLM Deception
A 600-game study of six language models playing Bullshit found that honesty prompts reduce deception, but also soften enforcement around the lies that remain.
Hardware Over Oracles: $0.01 TEE-Backed Randomness API (Offchain)
Chainlink VRF is overkill for gacha games. We built a $0.01 alternative using Intel TDX.
Garden
View allShorter notes and working definitions.
A* pathfinding in tactics games
A* is the algorithm that makes units move intelligently around obstacles—and it's the backbone of nearly every tactics game.
What is WebGPU? (and WebGPU vs. WebGL)
WebGPU is the modern graphics API for browsers—giving web apps direct access to GPU compute and better performance than aging WebGL.
What are shaders?
Shaders are small programs that run on the GPU to control how pixels and vertices look—essentially the paintbrushes of real-time graphics.
What is BuildKit in Docker?
BuildKit is Docker's modern builder that compiles images faster through parallelization, caching, and smarter layer management.
What is reinforcement learning?
Reinforcement learning trains agents through trial and error, learning from rewards and penalties rather than labeled examples.
What are state machines?
State machines model systems that can only be in one state at a time, transitioning based on inputs.
What are TEE verified servers?
TEEs let you run code in a secure enclave that even the server owner can't peek into—useful for private AI inference and verifiable randomness.
What is model quantization (INT4/INT8/FP8/FP16/FP32)?
Quantization shrinks model weights from 32-bit floats to smaller formats to save memory and run faster—with a small trade-off in accuracy.