2026 May
- CODA-DVD: Dark Vessel Detection from Orbit in Two HoursMy submission for the Liquid AI x DPhi Space 'AI in Space' hackathon: an on-board satellite AI pipeline that filters 98% of downlink bandwidth using LFM2.5-VL.HackathonSatelliteVLMEdge AI
- llama.cpp on Apple Silicon: 29 GGUF Benchmarks and a 200 t/s SurpriseI added llama.cpp benchmarks across eight model groups to the local LLM benchmark suite. Speculative decoding with Gemma 4 hit 206 tokens per second on an M3 Max. Here's how it compares.LLM InferenceApple SiliconBenchmarkingllama.cppGGUF
2026 April
2026 March
- PlayAble: An Accessible Retro Gaming Portal from Hackathon HeilbronnMy 10-year-old and I spent 24 hours at Hackathon Heilbronn turning a 26-year-old TV game into a browser-based accessible gaming portal, without writing a single line of code ourselves.HackathonAccessibilityAIGaming
- Three Weeks in Silicon Valley: Robotaxis, Agentic AI, and What Europe Gets WrongA project assignment in San Jose, friends at Applied Intuition and Zoox, and a 13-year-old at the German International School. What three weeks in Mountain View taught me about where we actually stand with AI and autonomous driving.Silicon ValleyAIAutonomous Driving
Projects
- CODA-DVDOn-board satellite AI pipeline for dark vessel detection. Three-stage cascaded filter discards clouds and empty ocean before transmission. 98% bandwidth saved.
- LLM Inference Benchmark HarnessA Python harness for systematic evaluation of LLM inference bottlenecks across backends, quantization formats, KV cache strategies, and long-context agentic workloads.
- PlayAbleAn accessible retro gaming portal that lets people with disabilities play classic games through voice commands, hand gestures, or keyboard. Built in 24 hours at Hackathon Heilbronn with zero manually written code.