Evenlight: I gave the AI the smallest job in the app, and measured why
说明与用途
Evenlight 应用测量天空颜色和太阳高度,生成包含从固定词汇表中挑选的名称的卡片。模型在从35个词中选择时失败后,任务被缩小为从三个选项中挑选,准确率提升至17/18。
问题
The app claims to measure only what it sees from a photo taken by the user, but a language model on the phone performed poorly at selecting a name for the evening from a fixed vocabulary, leading to a design decision to give the model a smaller task.
结果
The app successfully measures sky colour and sun altitude without external data, and the redesigned language‑model workflow achieves high accuracy for name selection while preserving privacy.
工作流
- 1. Capture a photo with the phone camera. 2. Sample eight horizontal colour bands from the image. 3. Compute sun altitude using stored coordinates and NOAA solar maths. 4. Match the most colourful band against a 35‑word vocabulary. 5. Generate a card with the colour bands, chosen name, date, and altitude. 6. Store the card locally; no network transmission.
- 7. Run the language model on‑device to select a name from a three‑choice list. 8. If the model fails, fall back to a template phrase.
- 9. Display a stack of recorded evenings, showing gaps where evenings were missed.
证据
The app claims exactly what it measures and nothing else.
The shutter is gated on nothing but enabled = !busy. No hour check, no sun‑altitude check, no scene check.
I ran it on the inputs the app would actually hand it, before writing any app code. Five designs, a 1B parameter open‑weight model on CPU, the same eighteen calls on the last two.
"choose from exactly these words" (the real 35‑word vocabulary) – 0/6 on‑list.
on‑list 18/18, single‑line 18/18, stable 1/6
- 记录日期: 2026-10-11T12:56:02.003Z