Skip to content
shaostassen.com

projects

Projects

School work and individual work, filterable by area. Case studies land here as they are written.

School work

Individual work

Bits → Messages

Embedded

A serial-communication simulator whose engine also drives a real device node — the same UART runs the diagram in the browser and the /dev/ttys* you open with screen.

protocols: six, compared

SerialUARTProtocolsPTYNode.jsTypeScriptReactSVGTeaching tool

case study →

Blaze and Heat

Robotics

A combat-robotics game with no hit points: the spinner stores real rotational energy, and the collision that dumps it is what decides whether armour shears off.

stored blade energy: 4302 J at 1910 RPM

Godot 4GDScriptJolt PhysicsRigid-body dynamicsGame AIHeadless benchmarks

in progress

case study →

Electrons → Instructions

Embedded

An interactive eleven-level descent from charge drifting in copper to a running program that puts a bit back on a pin — and every level can be broken on purpose.

levels: 11, each earned

Digital logicCMOSComputer architectureSVGReactTypeScriptTeaching tool

case study →

Emulation-Based Fault Injection Harness

Embedded

A campaign harness that glitches bare-metal firmware in emulation to measure which countermeasures actually stop a secure-boot bypass — across two instruction sets, with every result cross-checked against a second emulator.

exhaustive search: 95.9M fault pairs

Fault injectionEmbedded securityFirmwareCortex-MRISC-VEmulationPython

in progress

case study →

Local-First Imitation-Learning Platform

Robotics

The whole imitation-learning loop on one laptop — teleoperate a manipulation task in the browser, record demonstrations, train a policy, then watch that policy take the controls — with no GPU anywhere in it.

CPU training: 14 s on one core

Imitation learningBehavior cloningRobot teleoperationLeRobotPyTorchFastAPIWebSocketsNext.js

in progress

case study →

SpeechLens

ML · CV

A fully local language-ID and transcription pipeline — faster-whisper and Silero VAD behind an explicit anti-hallucination harness — running large-v3 at 3.9× realtime on a CPU with no GPU at all.

CPU throughput: 3.9× realtime (9950X, large-v3 int8)

ASRLanguage IDfaster-whisperSilero VADFastAPIPython

in progress

case study →

Remote ML Compute over Tailscale

Systems · HPC

A headless Ryzen 9 9950X reachable by name from anywhere over a private mesh — the CPU-only box that ran every experiment behind SpeechLens and SpeechForge.

unattended compute: ~15 h of studies in one session

TailscaleLinuxUbuntuPythonInfrastructure

in progress

case study →