bavaria, germany — applying to study computer science
I’m Robert — I build AI‑assisted software end to end, keep a few small machines running at home, and ship things I actually use. Abitur 2026, grade 1.7.
And yes, I actually do like em dashes. ;)
I develop with AI coding agents every day and I’m open about it: I scope the tasks and own the results. This is my own local tracking across my machines — not an estimate.
eight complete weeks · may 18 – july 12, 2026 · ≈ $7,892 api‑equivalent
codex · 4.18B · 60% · mostly gpt-5.5 claude code · 2.75B · 40% · fable-5 & opus-4-8
weekly ccusage aggregates, complete weeks only · updated july 15, 2026 · click a week for detail
My projects — the list updates as I build. Most are public, some stay private. I make things that actually benefit me, plus hobby projects I just think are cool — often deliberately oversized, to push AI‑assisted development to its limits.
A Bun monorepo — SvelteKit 2 / Svelte 5 in front, a Rust (Axum) workspace staged behind — where every page is prerendered from Markdown and YAML: no database, no API on the content path. Strict hash‑mode CSP, a hand‑rolled bilingual layer, and an Ask assistant streaming over server‑sent events; chat history stays in your browser.
One question — what is this track? — answered for messy inputs: noisy web video, playlists, local files. The same engine is exposed four ways: a CLI, a local HTTP API, a terminal UI, and a native SwiftUI app. Recognition starts local and free, with hosted services only as an opt‑in fallback.
An instrument stage and music studio for macOS: eleven fully synthesized instruments, a track editor with lanes, a drum step grid, velocity, loops and undo, playlists, and export to WAV, AIFF, ALAC or AAC at up to 96 kHz. The stage renders the music as light while you play.
A Rust automation runtime for Hypixel SkyBlock auction flipping. The constraints: live market data, several accounts at once, and a platform that actively looks for automation. Most of the work is in what it’s not allowed to do: blocklists, skip thresholds, price guards, a hard dry‑run/live boundary. A native macOS dashboard watches it over an SSH tunnel.
I’m from a village in Bavaria; school was a boarding school on lake Ammersee. My first projects, around year 9, were small and scrappy — a Python face tracker built on an AI vision model, game prototypes in Unreal Engine 5, Unity, and Godot. The projects grew up with me.
The most reliable way I learn systems is running them myself. It started with a Windows tower and a hardware phase — overclocking, file systems, PC building — until the interest tipped into software: Arch Linux on an old ThinkPad as the very first distro, no training wheels, then a rabbit hole of distributions. Today the MacBook is the work machine, orchestrating a CachyOS Legion 7 for AI training runs and an always‑on Raspberry Pi 5 over the local network. Windows had its years — the dual‑boot ones.
For four years I ran sound, lighting, and stage tech for my school’s events — the weekly assembly plus everything with an audience. The rest of the record: game master of a pen‑and‑paper group, student council, Model United Nations in Copenhagen, and two history awards I didn’t see coming.
Nothing here yet — honestly. The blog ships with the site and the pipeline is tested; the words are taking a little longer than the code. When the first note lands, rss.xml will have it first.
05 · the fastest way is email
Everything else — the CV in English and German, GitHub, RSS — lives in one place: