How this site was made
A clear split of who did what, because it matters. The AI media on this site was executed locally, on the €2,960 box the report measures - but the report was written and the website built by Claude Code (Anthropic's Claude, a cloud coding assistant) working with Alastair McDermott. The box ran the models; a cloud agent and a human did the planning, writing, and assembly. We'd rather tell you exactly who did what than imply the hardware built its own brochure.
Executed on the box - its own AI, nothing leaving the building
- The spoken audio: the local 30-billion-parameter model (Qwen3-30B-A3B) drafted each script (the podcast script lightly edited for tone), and it was voiced on the box - the two-voice audio overview by Chatterbox TTS (chosen by ear after Piper and Kokoro were rejected; see the audio quality verdict), the "Listen to this page" narrations and the explainer video by Piper. ffmpeg encoded the audio and video.
- The images: the hero, the social card, and the 50-image gallery were generated by FLUX.1-schnell via stable-diffusion.cpp - see the gallery and the quality verdict.
- The demonstrations and the numbers: meeting transcription (whisper) and document Q&A ran on the box, and every benchmark figure in the report is a local measurement.
The narration pipeline, timed on the box:
| Page | Script words | Model wrote it in | Voice took | Audio length | TTS speed |
|---|---|---|---|---|---|
| index | 154 | 2.5 s | 1.42 s | 53 s | 37.7× real-time |
| executive-briefing | 203 | 3.8 s | 1.65 s | 68 s | 41.2× real-time |
| capability-report | 256 | 5.6 s | 2.44 s | 107 s | 43.8× real-time |
Planned and built off the box - Claude Code + a human
- The benchmark design and pre-registration, this report's prose, the website code, the charts (Plotly/Python), and the prompts that directed the local generation were done by Claude Code - an AI coding assistant running on Anthropic's cloud - under Alastair McDermott's direction.
- One external AI call is disclosed: the frontier quality comparison sent eleven prompts to gpt-5.5 for about two US cents (report §13).
So: the local box proved it can do the AI work - narration, speech, images, transcription, analysis - at the speeds the report documents. Turning that into a written report and a website was the job of a cloud assistant and a person. Both halves are true; neither is hidden.
Brand
Styled with the HumanSpark brand kit v1.0.0: self-hosted Inter and JetBrains Mono, brand colour tokens, no Google Fonts. Kit provenance and content hash are recorded in brand-kit/KIT-VERSION, so a brand refresh is detectable rather than silently drifting.